Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/zhulf0804/3D-PointCloud
Papers and Datasets about Point Cloud.
https://github.com/zhulf0804/3D-PointCloud
autonomous-driving classification completion datasets detection generation monocular papers point-cloud registration segmentation
Last synced: 14 days ago
JSON representation
Papers and Datasets about Point Cloud.
- Host: GitHub
- URL: https://github.com/zhulf0804/3D-PointCloud
- Owner: zhulf0804
- Created: 2019-03-06T05:21:06.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2024-08-25T10:26:56.000Z (3 months ago)
- Last Synced: 2024-08-25T11:36:14.107Z (3 months ago)
- Topics: autonomous-driving, classification, completion, datasets, detection, generation, monocular, papers, point-cloud, registration, segmentation
- Language: Python
- Homepage:
- Size: 1.69 MB
- Stars: 2,329
- Watchers: 89
- Forks: 295
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-artificial-intelligence-research - Point Cloud
README
# 3D - Point Cloud
**Paper list** and **Datasets** about Point Cloud. Datasets can be found in [Datasets.md](https://github.com/zhulf0804/3D-PointCloud/blob/master/Datasets.md).
## Survey papers
- [A Comprehensive Survey and Taxonomy on Point Cloud Registration Based on Deep Learning](https://arxiv.org/pdf/2404.13830v1.pdf) [IJCAI 2024; [Github](https://github.com/yxzhang15/PCR)]
- [Sequential Point Clouds: A Survey](https://arxiv.org/pdf/2204.09337.pdf) [TPAMI 2024]
- [A Survey of Label-Efficient Deep Learning for 3D Point Clouds](https://arxiv.org/pdf/2305.19812.pdf) [TPAMI 2024; [Github](https://github.com/xiaoaoran/3D_label_efficient_learning)]
- [Surface Reconstruction from Point Clouds: A Survey and a Benchmark](https://arxiv.org/pdf/2205.02413.pdf) [TPAMI 2024]
- [End-to-end Autonomous Driving: Challenges and Frontiers](https://arxiv.org/pdf/2306.16927.pdf) [TPAMI 2024; [Github](https://github.com/OpenDriveLab/End-to-end-Autonomous-Driving)]
- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://arxiv.org/pdf/2206.09474.pdf) [IJCV 2023; [Github](https://github.com/pointscoder/awesome-3d-object-detection-for-autonomous-driving)]
- [Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey](https://arxiv.org/pdf/2202.13589.pdf) [TPAMI 2023; [Github](https://github.com/xiaoaoran/3d_url_survey)]
- [3D Object Detection from Images for Autonomous Driving: A Survey](https://arxiv.org/pdf/2202.02980.pdf) [TPAMI 2023; [Github](https://github.com/xinzhuma/3dodi-survey)]
- [Survey and Systematization of 3D Object Detection Models and Methods](https://arxiv.org/pdf/2201.09354v1.pdf) [TVC 2023]
- [Multi-Modal 3D Object Detection in Autonomous Driving: a Survey](https://arxiv.org/pdf/2106.12735.pdf) [IJCV 2023]
- [Cross-source Point Cloud Registration: Challenges, Progress and Prospects](https://arxiv.org/pdf/2305.13570.pdf) [Neurocomputing 2023]
- [Self-Supervised Learning for Point Clouds Data: A Survey](https://arxiv.org/pdf/2305.11881.pdf) [ESWA 2023]
- [Self-supervised Learning for Pre-Training 3D Point Clouds: A Survey](https://arxiv.org/pdf/2305.04691.pdf) [arXiv 2023]
- [Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review](https://arxiv.org/pdf/2304.10410v2.pdf) [IEEE T-IV 2023; [Project](https://radar-camera-fusion.github.io)]
- [Perception Datasets for Anomaly Detection in Autonomous Driving: A Survey](https://arxiv.org/pdf/2302.02790.pdf) [IEEE T-IV 2023]
- [Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe](https://arxiv.org/pdf/2209.05324.pdf) [TPAMI 2023; [Github](https://github.com/OpenDriveLab/BEVPerception-Survey-Recipe)]
- [3D Vision with Transformers: A Survey](https://arxiv.org/pdf/2208.04309.pdf) [arXiv 2022; [Github](https://github.com/lahoud/3d-vision-transformers)]
- [Vision-Centric BEV Perception: A Survey](https://arxiv.org/pdf/2208.02797.pdf) [arXiv 2022; [Github](https://github.com/4DVLab/Vision-Centric-BEV-Perception)]
- [Transformers in 3D Point Clouds: A Survey](https://arxiv.org/pdf/2205.07417.pdf) [arXiv 2022]
- [A Survey of Robust LiDAR-based 3D Object Detection Methods for Autonomous Driving](https://arxiv.org/pdf/2204.00106.pdf) [arXiv 2022]
- [A Survey of Non-Rigid 3D Registration](https://arxiv.org/pdf/2203.07858.pdf) [Eurographics 2022]
- [Comprehensive Review of Deep Learning-Based 3D Point Clouds Completion Processing and Analysis](https://arxiv.org/pdf/2203.03311.pdf) [TITS 2022]
- [Multi-modal Sensor Fusion for Auto Driving Perception: A Survey](https://arxiv.org/pdf/2202.02703.pdf) [arXiv 2022]
- [3D Object Detection for Autonomous Driving: A Survey](https://arxiv.org/pdf/2106.10823.pdf) [Pattern Recognition 2022; [Github](https://github.com/rui-qian/SoTA-3D-Object-Detection)]
- [3D Semantic Scene Completion: a Survey](https://arxiv.org/pdf/2103.07466.pdf) [IJCV 2022]
- [Deep Learning based 3D Segmentation: A Survey](https://arxiv.org/pdf/2103.05423.pdf) [arXiv 2021]
- [A comprehensive survey on point cloud registration](https://arxiv.org/pdf/2103.02690.pdf) [arXiv 2021]
- [Deep Learning for 3D Point Clouds: A Survey](https://arxiv.org/pdf/1912.12033.pdf) [TPAMI 2020; [Github](https://github.com/QingyongHu/SoTA-Point-Cloud)]
- [A Comprehensive Performance Evaluation of 3D Local Feature Descriptors](https://www.researchgate.net/profile/Yulan_Guo/publication/274387466_A_Comprehensive_Performance_Evaluation_of_3D_Local_Feature_Descriptors/links/552b4a5b0cf29b22c9c1a6d2/A-Comprehensive-Performance-Evaluation-of-3D-Local-Feature-Descriptors.pdf) [IJCV 2016]
## 2024
- ECCV
- [OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation](https://arxiv.org/abs/2309.00616)[`open-vocabulary`; [Github](https://github.com/Pointcept/OpenIns3D)]
- [Approaching Outside: Scaling Unsupervised 3D Object Detection from 2D Scene](https://arxiv.org/pdf/2407.08569v1) [`det`]
- [Global-Local Collaborative Inference with LLM for Lidar-Based Open-Vocabulary Detection](https://arxiv.org/pdf/2407.08931v1) [`det`]
- [OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection](https://arxiv.org/pdf/2407.10753v1) [`det`]
- [SEED: A Simple and Effective 3D DETR in Point Clouds](https://arxiv.org/pdf/2407.10749v1) [`det`]
- [DSPDet3D: Dynamic Spatial Pruning for 3D Small Object Detection](https://arxiv.org/pdf/2305.03716.pdf) [`det`; [PyTorch](https://github.com/xuxw98/DSPDet3D)]
- [General Geometry-aware Weakly Supervised 3D Object Detection](https://arxiv.org/pdf/2407.13748v1) [`det`; [PyTorch](https://github.com/gwenzhang/GGA)]
- [SegPoint: Segment Any Point Cloud via Large Language Model](https://arxiv.org/pdf/2407.13761v1) [`seg`]
- [Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models](https://arxiv.org/pdf/2407.13642v1) [`seg`]
- [ItTakesTwo: Leveraging Peer Representations for Semi-supervised LiDAR Semantic Segmentation](https://arxiv.org/pdf/2407.07171v1) [`seg`]
- [RAPiD-Seg: Range-Aware Pointwise Distance Distribution Networks for 3D LiDAR Segmentation](https://arxiv.org/pdf/2407.10159v1) [`seg`]
- [3×2: 3D Object Part Segmentation by 2D Semantic Correspondences](https://arxiv.org/pdf/2407.09648v1) [`seg`]
- [Dual-level Adaptive Self-Labeling for Novel Class Discovery in Point Cloud Segmentation](https://arxiv.org/pdf/2407.12489v1) [`seg`]
- [SFPNet: Sparse Focal Point Network for Semantic Segmentation on General LiDAR Point Clouds](https://arxiv.org/pdf/2407.11569v1) [`seg`]
- [HGL: Hierarchical Geometry Learning for Test-time Adaptation in 3D Point Cloud Segmentation](https://arxiv.org/pdf/2407.12387v1) [`seg`; [PyTorch](https://github.com/tpzou/HGL)]
- [Part2Object: Hierarchical Unsupervised 3D Instance Segmentation](https://arxiv.org/pdf/2407.10084v1) [`seg`; [PyTorch](https://arxiv.org/pdf/2407.10084v1)]
- [4D Contrastive Superflows are Dense 3D Representation Learners](https://arxiv.org/pdf/2407.06190v1) [`pre-training`]
- [Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape Data](https://arxiv.org/pdf/2407.10200v1) [`pre-training`]
- [Explicitly Guided Information Interaction Network for Cross-modal Point Cloud Completion](https://arxiv.org/pdf/2407.02887) [`completion`; [PyTorch](https://github.com/WHU-USI3DV/EGIInet)]
- [T-CorresNet: Template Guided 3D Point Cloud Completion with Correspondence Pooling Query Generation Strategy](https://arxiv.org/pdf/2407.05008) [`completion`; [Github](https://github.com/df-boy/T-CorresNet)]
- [GaussReg: Fast 3D Registration with Gaussian Splatting](https://arxiv.org/pdf/2407.05254v1) [`registration`]
- [PointRegGPT: Boosting 3D Point Cloud Registration using Generative Point-Cloud Pairs for Training](https://arxiv.org/pdf/2407.14054v1) [`registration`; [PyTorch](https://github.com/Chen-Suyi/PointRegGPT)]
- [PARE-Net: Position-Aware Rotation-Equivariant Networks for Robust Point Cloud Registration](https://arxiv.org/pdf/2407.10142) [`registration`; [PyTorch](https://github.com/yaorz97/PARENet)]
- [ML-SemReg: Boosting Point Cloud Registration with Multi-level Semantic Consistency](https://arxiv.org/pdf/2407.09862v1) [`registration`; [PyTorch](https://github.com/Laka-3DV/ML-SemReg)]
- [Correspondence-Free SE(3) Point Cloud Registration in RKHS via Unsupervised Equivariant Learning](https://arxiv.org/pdf/2407.20223v1) [`registration`; [Project](https://sites.google.com/view/eccv24-equivalign)]
- [UMERegRobust - Universal Manifold Embedding Compatible Features for Robust Point Cloud Registration](https://arxiv.org/pdf/2408.12380) [`registration`; [PyTorch](https://github.com/yuvalH9/UMERegRobust)]
- [Transferable 3D Adversarial Shape Completion using Diffusion Models](https://arxiv.org/pdf/2407.10077v1) [`adversarial attack`]
- [R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detection](https://arxiv.org/pdf/2407.10862v1) [`anomaly detection`]
- CVPR
- [Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis](https://arxiv.org/pdf/2403.01439.pdf) [`pre-training`; [PyTorch](https://github.com/LMD0311/DAPT)]
- [HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenes](https://arxiv.org/pdf/2403.02769v1.pdf) [`det`]
- [Commonsense Prototype for Outdoor Unsupervised 3D Object Detection](https://arxiv.org/pdf/2404.16493) [`det`; [PyTorch](https://github.com/hailanyi/CPD)]
- [Learning Occupancy for Monocular 3D Object Detection](https://arxiv.org/pdf/2305.15694.pdf) [`det`; [Github](https://github.com/SPengLiang/OccupancyM3D)]
- [Point Transformer V3: Simpler, Faster, Stronger](https://arxiv.org/pdf/2312.10035v1.pdf) [`seg`, `det`; [Github](https://github.com/pointcept/pointtransformerv3)]
- [OneFormer3D: One Transformer for Unified Point Cloud Segmentation](https://arxiv.org/pdf/2311.14405.pdf) [`seg`; [Github](https://github.com/filaPro/oneformer3d)]
- [Rethinking Few-shot 3D Point Cloud Semantic Segmentation](https://arxiv.org/pdf/2403.00592.pdf) [`seg`; [PyTorch](https://github.com/ZhaochongAn/COSeg)]
- [CurveCloudNet: Processing Point Clouds with 1D Structure](https://arxiv.org/pdf/2303.12050v1.pdf) [`seg`]
- [UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes](https://arxiv.org/pdf/2303.14541.pdf) [`seg`; [Project](https://rozdavid.github.io/unscene3d)]
- [No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentation](https://arxiv.org/pdf/2404.04050.pdf) [`seg`; [PyTorch](https://github.com/yangyangyang127/Seg-NN)]
- [TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation](https://arxiv.org/pdf/2407.09751v1) [`seg`]
- [GeoAuxNet: Towards Universal 3D Representation Learning for Multi-sensor Point Clouds](https://arxiv.org/pdf/2403.19220) [`seg`; [PyTorch](https://github.com/zhangshengjun2019/GeoAuxNet)]
- [Multi-Space Alignments Towards Universal LiDAR Segmentation](https://arxiv.org/pdf/2405.01538v1) [`seg`; [Github](https://github.com/youquanl/M3Net)]
- [KPConvX: Modernizing Kernel Point Convolution with Kernel Attention](https://arxiv.org/pdf/2405.13194) [`cls`, `seg`]
- [X-3D: Explicit 3D Structure Modeling for Point Cloud Recognition](https://arxiv.org/pdf/2404.15010.pdf) [`cls`, `seg`; [PyTorch](https://github.com/sunshuofeng/X-3D)]
- [Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding](https://arxiv.org/pdf/2312.02244) [`cls`, `seg`; [PyTorch](https://github.com/gfmei/GeoZe)]
- [Coupled Laplacian Eigenmaps for Locally-Aware 3D Rigid Point Cloud Matching](https://arxiv.org/pdf/2402.17372v1.pdf) [`matching`]
- [Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension](https://arxiv.org/pdf/2403.03532.pdf) [`registration`; [Github](https://github.com/liuQuan98/EYOC)]
- [Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes](https://arxiv.org/pdf/2404.04557v1.pdf) [`registration`; [Github](https://github.com/zhiyuanYU134/MIRETR)]
- [FastMAC: Stochastic Spectral Sampling of Correspondence Graph](https://arxiv.org/pdf/2403.08770.pdf) [`registration`; [Github](https://github.com/Forrest-110/FastMAC)]
- [Scalable 3D Registration via Truncated Entry-wise Absolute Residuals](https://arxiv.org/pdf/2404.00915.pdf) [`registration`; [Github](https://github.com/tyhuang98/TEAR-release)]
- [Category-Level Multi-Part Multi-Joint 3D Shape Assembly](https://arxiv.org/pdf/2303.06163v1.pdf) [`shape assembly`]
- [Symphonize 3D Semantic Scene Completion with Contextual Instance Queries](https://arxiv.org/pdf/2306.15670.pdf) [`semantic scene completion`; [PyTorch](https://github.com/hustvl/Symphonies)]
- [PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation](https://arxiv.org/pdf/2306.10013.pdf) [`semantic occupancy prediction`; [Github](https://github.com/Robertwyq/PanoOcc)]
- [Visual Point Cloud Forecasting enables Scalable Autonomous Driving](https://arxiv.org/pdf/2312.17655.pdf) [`autonomous driving`; [Github](https://github.com/OpenDriveLab/ViDAR)]
- [Object Dynamics Modeling with Hierarchical Point Cloud-based Representations](https://arxiv.org/pdf/2312.00068) [`autonomous driving`; [PyTorch](https://github.com/prashkmr/GLiDR)]
- [Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes](https://arxiv.org/pdf/2403.01414v1.pdf) [`reconstruction`]
- [Unleashing Network Potentials for Semantic Scene Completion](https://arxiv.org/pdf/2403.07560v1.pdf) [`completion`]
- [FSC: Few-point Shape Completion](https://arxiv.org/pdf/2403.07359v1.pdf) [`completion`]
- [Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange](https://arxiv.org/pdf/2404.07504v1.pdf) [`self-supervised`; [Github](https://github.com/YanhaoWu/OESSL)]
- [GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding](https://arxiv.org/pdf/2403.09639.pdf) [`self-supervised`]
- [SemCity: Semantic Scene Generation with Triplane Diffusion](https://arxiv.org/pdf/2403.07773v1.pdf) [`generation`]
- [Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds](https://arxiv.org/pdf/2403.05247.pdf) [`adversarial attack`; [Github](https://github.com/TRLou/HiT-ADV)]
- [StraightPCF: Straight Point Cloud Filtering](https://arxiv.org/pdf/2405.08322v1) [`filtering`; [Github](https://github.com/ddsediri/StraightPCF)]
- [Unsupervised Occupancy Learning from Sparse Point Cloud](https://arxiv.org/pdf/2404.02759) [`reconstruction`]
- [Local-consistent Transformation Learning for Rotation-invariant Point Cloud Analysis](https://arxiv.org/pdf/2403.11113) [`rotation invariance`; [PyTorch](https://github.com/wdttt/LocoTrans)]
- [Text2Loc: 3D Point Cloud Localization from Natural Language](https://arxiv.org/pdf/2311.15977) [`localization`; [PyTorch](https://github.com/Yan-Xia/Text2Loc)]
- AAAI
- [iDet3D: Towards Efficient Interactive Object Detection for LiDAR Point Clouds](https://arxiv.org/pdf/2312.15449.pdf) [`det`]
- [CMDA: Cross-Modal and Domain Adversarial Adaptation for LiDAR-Based 3D Object Detection](https://arxiv.org/pdf/2403.03721v1.pdf) [`det`]
- [SimDistill: Simulated Multi-modal Distillation for BEV 3D Object Detection](https://arxiv.org/pdf/2303.16818.pdf) [`det`; [Github](https://github.com/ViTAE-Transformer/BEVSimDet)]
- [Semi-supervised 3D Object Detection with PatchTeacher and PillarMix](https://arxiv.org/pdf/2407.09787v1) [`det`]
- [PointCVaR: Risk-optimized Outlier Removal for Robust 3D Point Cloud Classification](https://arxiv.org/pdf/2307.10875.pdf) [`cls`; [PyTorch](https://github.com/shinke-li/pointcvar)]
- [NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fields](https://arxiv.org/pdf/2304.14811.pdf) [`autonomous driving`; [Github](https://github.com/fudan-zvg/NeRF-LiDAR)]
- [CMG-Net: Robust Normal Estimation for Point Clouds via Chamfer Normal Distance and Multi-scale Geometry](https://arxiv.org/pdf/2312.09154v1.pdf) [`normal estimation`]
- [3D Visibility-aware Generalizable Neural Radiance Fields for Interacting Hands](https://arxiv.org/pdf/2401.00979v1.pdf) [`NeRF`]
- [CRA-PCN: Point Cloud Completion with Intra- and Inter-level Cross-Resolution Transformers](https://arxiv.org/pdf/2401.01552.pdf) [`completion`; [PyTorch](https://github.com/EasyRy/CRA-PCN)]
- [PointAttN: You Only Need Attention for Point Cloud Completion](https://arxiv.org/pdf/2203.08485v1.pdf) [`completion`; [PyTorch](https://github.com/ohhhyeahhh/PointAttN)]
- [EPCL: Frozen CLIP Transformer is An Efficient Point Cloud Encoder](https://arxiv.org/pdf/2212.04098.pdf) [`pre-training`]
- [MM-Point: Multi-View Information-Enhanced Multi-Modal Self-Supervised 3D Point Cloud Understanding](https://arxiv.org/pdf/2402.10002) [`self-supervised`]
- [DHGCN: Dynamic Hop Graph Convolution Network for Self-Supervised Point Cloud Learning](https://arxiv.org/pdf/2401.02610) [`self-supervised`]
- [SPEAL: Skeletal Prior Embedded Attention Learning for Cross-Source Point Cloud Registration](https://arxiv.org/pdf/2312.08664.pdf) [`registration`]
- [DeepPointMap: Advancing LiDAR SLAM with Unified Neural Descriptors](https://arxiv.org/pdf/2312.02684.pdf) [`matching`; [Github](https://github.com/ZhangXiaze/DeepPointMap)]
- [Arbitrary-Scale Point Cloud Upsampling by Voxel-Based Network with Latent Geometric-Consistent Learning](https://arxiv.org/pdf/2403.05117.pdf) [`upsampling`]
- [Modeling Continuous Motion for 3D Point Cloud Object Tracking](https://arxiv.org/pdf/2303.07605v1.pdf) [`tracking`]
- Others
- [3D Geometric Shape Assembly via Efficient Point Cloud Matching](https://arxiv.org/pdf/2407.10542v1) [`assembly`; ICML]
- [Fully Sparse Fusion for 3D Object Detection](https://arxiv.org/pdf/2304.12310v1.pdf) [`det`; [Github](https://github.com/BraveGroup/FullySparseFusion); TPAMI]
- [Fast-BEV: A Fast and Strong Bird’s-Eye View Perception Baseline](https://arxiv.org/pdf/2301.12511v1.pdf) [`det`; [PyTorch](https://github.com/Sense-GVT/Fast-BEV)]
- [An Effective Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds](https://arxiv.org/pdf/2303.12535v1.pdf) [`tracking`; [PyTorch](https://github.com/Ghostish/Open3DSOT); TPAMI]
- [Exploring Point-BEV Fusion for 3D Point Cloud Object Tracking with Transformer](https://arxiv.org/pdf/2208.05216.pdf) [`tracking`; [PyTorch](https://github.com/Jasonkks/PTTR)]
- [Efficient and Robust Point Cloud Registration via Heuristics-guided Parameter Search](https://arxiv.org/pdf/2404.06155v1.pdf) [`registration`; [Github](https://github.com/tyhuang98/HERE-release); TPAMI]
- [RIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registration](https://arxiv.org/pdf/2209.13252.pdf) [`registration`; TPAMI]
- [Benchmarking the Robustness of LiDAR Semantic Segmentation Models](https://arxiv.org/pdf/2301.00970v1.pdf) [`seg`; IJCV]
- [Position-Guided Point Cloud Panoptic Segmentation Transformer](https://arxiv.org/pdf/2303.13509v1.pdf) [`seg`; [Github](https://github.com/SmartBot-PJLab/P3Former); IJCV]
- [PointWavelet: Learning in Spectral Domain for 3D Point Cloud Analysis](https://arxiv.org/pdf/2302.05201.pdf) [`cls`, `seg`; TNNLS]
- [CP-Net: Contour-Perturbed Reconstruction Network for Self-Supervised Point Cloud Learning](https://arxiv.org/pdf/2201.08215v1.pdf) [`self-supervised`; TMM]
- [Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast](https://arxiv.org/pdf/2305.19623.pdf) [`self-supervised learning`; [Github](https://github.com/Asterisci/Point-GCC); ACM MM]
- [StereoScene: BEV-Assisted Stereo Matching Empowers 3D Semantic Scene Completion](https://arxiv.org/pdf/2303.13959v1.pdf) [`semantic scene completion`; [PyTorch](https://github.com/Arlo0o/StereoScene); IJCAI]
- [Q-REG: End-to-End Trainable Point Cloud Registration with Surface Curvature](https://arxiv.org/pdf/2309.16023.pdf) [`registration`; [Github](https://github.com/jinsz/Q-REG); 3DV]
- [Pix4Point: Image Pretrained Transformers for 3D Point Cloud Understanding](https://arxiv.org/pdf/2208.12259.pdf) [`pretraining`; [Github](https://github.com/guochengqian/Pix4Point); 3DV]
- [OCBEV: Object-Centric BEV Transformer for Multi-View 3D Object Detection](https://arxiv.org/pdf/2306.01738.pdf) [`det`; 3DV]
- [MAELi -- Masked Autoencoder for Large-Scale LiDAR Point Clouds](https://arxiv.org/pdf/2212.07207.pdf) [`self-supervised`; WACV]
- [Top-Down Beats Bottom-Up in 3D Instance Segmentation](https://arxiv.org/pdf/2302.02871.pdf) [`seg`; [PyTorch](https://github.com/SamsungLabs/td3d); WACV]
- [Hierarchical Point Attention for Indoor 3D Object Detection](https://arxiv.org/pdf/2301.02650v2) [`det`; [Github](https://github.com/salesforce/Hierarchical_Point_Attention); ICRA]
- [LiDARFormer: A Unified Transformer-based Multi-task Network for LiDAR Perception](https://arxiv.org/pdf/2303.12194v1.pdf) [`det`, `seg`; ICRA]
- [FF-LOGO: Cross-Modality Point Cloud Registration with Feature Filtering and Local to Global Optimization](https://arxiv.org/pdf/2309.08966.pdf) [`registration`; ICRA]
- [SGFeat: Salient Geometric Feature for Point Cloud Registration](https://arxiv.org/pdf/2309.06207.pdf) [`registration`; ICRA]
- [3D-OAE: Occlusion Auto-Encoders for Self-Supervised Learning on Point Clouds](https://arxiv.org/pdf/2203.14084.pdf) [`self-supervised`; [Github](https://github.com/junshengzhou/3D-OAE); ICRA]
- [V2I-Calib: A Novel Calibration Approach for Collaborative Vehicle and Infrastructure LiDAR Systems](https://arxiv.org/pdf/2407.10195v1) [`calibration`; IROS]
- [Occ-BEV: Multi-Camera Unified Pre-training via 3D Scene Reconstruction](https://arxiv.org/pdf/2305.18829.pdf) [`det`, `semantic occupancy prediction`; [PyTorch](https://github.com/chaytonmin/Occ-BEV); RAL]
- [Robust Partial-to-Partial Point Cloud Registration in a Full Range](https://arxiv.org/pdf/2111.15606.pdf) [`registration`; [PyTorch](https://github.com/paul007pl/GMCNet); RAL]
- [Joint Representation Learning for Text and 3D Point Cloud](https://arxiv.org/pdf/2301.07584v1.pdf) [`pre-training`; [Github](https://github.com/LeapLabTHU/Text4Point); PR]
- [POS-BERT: Point Cloud One-Stage BERT Pre-Training](https://arxiv.org/pdf/2204.00989.pdf) [`pre-training`; [Github](https://github.com/fukexue/POS-BERT); ESWA]
- arXiv
- [Diff-PCR: Diffusion-Based Correspondence Searching in Doubly Stochastic Matrix Space for Point Cloud Registration](https://arxiv.org/pdf/2401.00436.pdf) [`registration`]
- [BiEquiFormer: Bi-Equivariant Representations for Global Point Cloud Registration](https://arxiv.org/pdf/2407.08729v1) [`registration`]
## 2023
- ICCV
- [Scene as Occupancy](https://arxiv.org/pdf/2306.02851.pdf) [`autonomous driving`; [PyTorch](https://github.com/OpenDriveLab/OccNet)]
- [OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction](https://arxiv.org/pdf/2304.05316v1.pdf) [`semantic occupancy prediction`; [PyTorch](https://github.com/zhangyp15/OccFormer)]
- [Cross Modal Transformer via Coordinates Encoding for 3D Object Dectection](https://arxiv.org/pdf/2301.01283v1.pdf) [`det`; [Github](https://github.com/junjie18/CMT)]
- [Once Detected, Never Lost: Surpassing Human Performance in Offline LiDAR based 3D Object Detection](https://arxiv.org/pdf/2304.12315v1.pdf) [`det`; [PyTorch](https://github.com/tusen-ai/SST)]
- [Efficient Transformer-based 3D Object Detection with Dynamic Token Halting](https://arxiv.org/pdf/2303.05078v1.pdf) [`det`]
- [Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection](https://arxiv.org/pdf/2303.11926v1.pdf) [`det`; [Github](https://github.com/exiawsh/StreamPETR)]
- [PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images](https://arxiv.org/pdf/2206.01256.pdf) [`autonomous driving`; [Github](https://github.com/megvii-research/PETR)]
- [SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving](https://arxiv.org/abs/2303.09551v1) [`autonomous driving`; [PyTorch](https://github.com/weiyithu/SurroundOcc)]
- [SupFusion: Supervised LiDAR-Camera Fusion for 3D Object Detection](https://arxiv.org/pdf/2309.07084v1.pdf) [`det`; [Github](https://github.com/IranQin/SupFusion)]
- [Object as Query: Lifting any 2D Object Detector to 3D Detection](https://arxiv.org/pdf/2301.02364) [`det`; [PyTorch](https://github.com/tusen-ai/MV2D)]
- [SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection](https://arxiv.org/pdf/2304.14340v1.pdf) [`det`; [Github](https://github.com/yichen928/SparseFusion)]
- [DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection](https://arxiv.org/pdf/2304.13031v1.pdf) [`det`; [PyTorch](https://github.com/AIR-DISCOVER/DQS3D)]
- [Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction](https://arxiv.org/pdf/2304.00967v1.pdf) [`det`; [Github](https://github.com/Sense-X/HoP)]
- [Robo3D: Towards Robust and Reliable 3D Perception against Corruptions](https://arxiv.org/pdf/2303.17597.pdf) [`seg`, `det`; [Github](https://github.com/ldkong1205/Robo3D)]
- [Clustering based Point Cloud Representation Learning for 3D Analysis](https://arxiv.org/pdf/2307.14605.pdf) [`seg`, `det`; [PyTorch](https://github.com/FengZicai/Cluster3Dseg)]
- [MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception](https://arxiv.org/pdf/2211.10593.pdf) [`seg`, `det`]
- [DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds](https://arxiv.org/pdf/2306.06023.pdf) [`det`; [Github](https://github.com/PJLab-ADG/DetZero)]
- [Efficient 3D Semantic Segmentation with Superpoint Transformer](https://arxiv.org/pdf/2306.08045.pdf) [`seg`; [PyTorch](https://github.com/drprojects/superpoint_transformer)]
- [Generalized Few-Shot Point Cloud Segmentation Via Geometric Words](https://arxiv.org/pdf/2309.11222.pdf) [`seg`]
- [Rethinking Range View Representation for LiDAR Segmentation](https://arxiv.org/pdf/2303.05367v1.pdf) [`seg`]
- [Retro-FPN: Retrospective Feature Pyramid Network for Point Cloud Semantic Segmentation](https://arxiv.org/pdf/2308.09314.pdf) [`seg`; [Github](https://github.com/AllenXiangX/Retro-FPN)]
- [Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic Segmentation](https://arxiv.org/pdf/2308.11166.pdf) [`seg`; [PyTorch](https://github.com/SmiletoE/HPAL)]
- [PointCLIP V2: Adapting CLIP for Powerful 3D Open-world Learning](https://arxiv.org/pdf/2211.11682.pdf) [`pre-training`; [Github](https://github.com/yangyangyang127/PointCLIP_V2)]
- [Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models](https://arxiv.org/pdf/2307.14971.pdf) [`pre-training`; [PyTorch](https://github.com/wangzy22/TAP)]
- [Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models](https://arxiv.org/pdf/2304.07221.pdf) [`pre-training`; [PyTorch](https://github.com/zyh16143998882/ICCV23-IDPT)]
- [CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training](https://arxiv.org/pdf/2210.01055.pdf) [`pre-training`; [PyTorch](https://github.com/tyhuang0428/CLIP2Point)]
- [Implicit Autoencoder for Point Cloud Self-supervised Representation Learning](https://arxiv.org/pdf/2201.00785.pdf) [`self-supervised`; [PyTorch](https://github.com/SimingYan/IAE)]
- [Ponder: Point Cloud Pre-training via Neural Rendering](https://arxiv.org/pdf/2301.00157v1.pdf) [`self-supervised`; [Github](https://dihuangdh.github.io/ponder/)]
- [You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentation](https://arxiv.org/pdf/2304.11762v1.pdf) [`annotation`; [PyTorch](https://github.com/nerminsamet/seedal)]
- [Point-TTA: Test-Time Adaptation for Point Cloud Registration Using Multitask Meta-Auxiliary Learning](https://arxiv.org/pdf/2308.16481.pdf) [`registration`]
- [RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration](https://arxiv.org/pdf/2303.12384.pdf) [`registration`; [PyTorch](https://github.com/IRMVLab/RegFormer)]
- [PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registration](https://arxiv.org/pdf/2308.04782.pdf) [`registration`]
- [Density-invariant Features for Distant Point Cloud Registration](https://arxiv.org/pdf/2307.09788.pdf) [`registration`; [PyTorch](https://github.com/liuQuan98/GCL)]
- [AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration](https://arxiv.org/pdf/2309.11170.pdf) [`generation`, `registration`]
- [GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation](https://arxiv.org/pdf/2211.16762.pdf) [`reconstruction`; [PyTorch](https://github.com/rsy6318/GeoUDF)]
- [P2C: Self-Supervised Point Cloud Completion from Single Partial Clouds](https://arxiv.org/pdf/2307.14726.pdf) [`completion`; [PyTorch](https://github.com/CuiRuikai/Partial2Complete)]
- [Leveraging SE(3) Equivariance for Learning 3D Geometric Shape Assembly](https://arxiv.org/pdf/2309.06810v1.pdf) [`assembly`; [Project](https://crtie.github.io/SE-3-part-assembly/)]
- [TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses](https://arxiv.org/pdf/2306.05888.pdf) [`tracking`]
- CVPR
- [FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation](https://arxiv.org/pdf/2307.01492.pdf) [`semantic occupancy prediction`; [Github](https://github.com/NVlabs/FB-BEV); CVPRW]
- [Planning-oriented Autonomous Driving](https://openaccess.thecvf.com/content/CVPR2023/papers/Hu_Planning-Oriented_Autonomous_Driving_CVPR_2023_paper.pdf) [`autonomous driving`; [PyTorch](https://github.com/OpenDriveLab/UniAD)]
- [MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences](https://arxiv.org/pdf/2306.03206.pdf) [`det`]
- [FrustumFormer: Adaptive Instance-aware Resampling for Multi-view 3D Detection](https://arxiv.org/pdf/2301.04467v1.pdf) [`det`]
- [Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild](https://arxiv.org/pdf/2207.10660.pdf) [`det`; [PyTorch](https://github.com/facebookresearch/omni3d)]
- [BEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detection](https://arxiv.org/pdf/2303.08498v1.pdf) [`det`; [PyTorch](https://github.com/ADLab-AutoDrive/BEVHeight)]
- [TorchSparse++: Efficient Point Cloud Engine](https://openaccess.thecvf.com/content/CVPR2023W/WAD/papers/Tang_TorchSparse_Efficient_Point_Cloud_Engine_CVPRW_2023_paper.pdf) [`engine`; [PyTorch](https://github.com/mit-han-lab/torchsparse)]
- [Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object Detection](https://arxiv.org/pdf/2306.01438.pdf) [`det`; [PyTorch](https://github.com/JessieW0806/Bi-LRFusion)]
- [NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localization](https://arxiv.org/pdf/2305.17763.pdf) [`localization`]
- [Long Range Pooling for 3D Large-Scale Scene Understanding](https://arxiv.org/pdf/2301.06962v1.pdf) [`seg`]
- [PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models](https://arxiv.org/pdf/2212.01558.pdf) [`seg`]
- [GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds](https://arxiv.org/pdf/2305.16404.pdf) [`seg`; [PyTorch](https://github.com/vLAR-group/GrowSP)]
- [MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling with Informative-Preserved Reconstruction and Self-Distilled Consistency](https://arxiv.org/pdf/2212.09948.pdf) [`seg`, `det`]
- [3D Registration with Maximal Cliques](https://arxiv.org/pdf/2305.10854.pdf) [`registration`; [Github](https://github.com/zhangxy0517/3D-Registration-with-Maximal-Cliques)]
- [DynStatF: An Efficient Feature Fusion Strategy for LiDAR 3D Object Detection](https://arxiv.org/pdf/2305.15219.pdf) [`det`; CVPRW]
- [GeoMAE: Masked Geometric Target Prediction for Self-supervised Point Cloud Pre-Training](https://arxiv.org/pdf/2305.08808.pdf) [`self-supervised`; [Github](https://github.com/Tsinghua-MARS-Lab/GeoMAE)]
- [PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer](https://arxiv.org/pdf/2305.06621.pdf) [`det`; [Github](https://github.com/Nightmare-n/PVT-SSD)]
- [SHS-Net: Learning Signed Hyper Surfaces for Oriented Normal Estimation of Point Clouds](https://arxiv.org/pdf/2305.05873.pdf) [`normal estimation`; [PyTorch](https://github.com/LeoQLi/SHS-Net)]
- [Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving](https://arxiv.org/pdf/2305.06242.pdf) [`autonomous driving`; [PyTorch](https://github.com/OpenDriveLab/ThinkTwice)]
- [Self-supervised Pre-training with Masked Shape Prediction for 3D Scene Understanding](https://arxiv.org/pdf/2305.05026.pdf) [`self-supervised`]
- [PointCMP: Contrastive Mask Prediction for Self-supervised Learning on Point Cloud Videos](https://arxiv.org/pdf/2305.04075.pdf) [`self-supervised`]
- [Point2Vec for Self-Supervised Representation Learning on Point Clouds](https://arxiv.org/pdf/2303.16570.pdf) [`self-supervised`; [Project](https://point2vec.ka.codes); CVPRW]
- [PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds](https://arxiv.org/pdf/2305.04925.pdf) [`det`]
- [Self-Supervised 3D Scene Flow Estimation Guided by Superpoints](https://arxiv.org/pdf/2305.02528.pdf) [`scene flow`; [Github](https://github.com/supersyq/SPFlowNet)]
- [Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent with Learned Distance Functions](https://arxiv.org/pdf/2304.11846v1.pdf) [`upsampling`; [PyTorch](https://github.com/yunhe20/Grad-PU)]
- [SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation](https://arxiv.org/pdf/2212.04493.pdf) [`completion`, `reconstruction`, `generation`; [Github](https://github.com/yccyenchicheng/SDFusion)]
- [Fast Point Cloud Generation with Straight Flows](https://arxiv.org/pdf/2212.01747.pdf) [`generation`]
- [LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillation](https://arxiv.org/pdf/2304.11379v1.pdf) [`seg`; [Github](https://github.com/songw-zju/LiDAR2Map)]
- [Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection](https://arxiv.org/pdf/2304.09446v1.pdf) [`det`; [PyTorch](https://github.com/WoodwindHu/DTS)]
- [Curricular Object Manipulation in LiDAR-based Object Detection](https://arxiv.org/pdf/2304.04248v1.pdf) [`det`; [PyTorch](https://github.com/ZZY816/COM)]
- [Exploiting the Complementarity of 2D and 3D Networks to Address Domain-Shift in 3D Semantic Segmentation](https://arxiv.org/pdf/2304.02991v1.pdf) [CVPRW]
- [Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detection](https://arxiv.org/pdf/2304.01464v1.pdf) [`det`; [PyTorch](https://github.com/azhuantou/HSSDA)]
- [IterativePFN: True Iterative Point Cloud Filtering](https://arxiv.org/pdf/2304.01529v1.pdf) [`filtering`; [Github](https://github.com/ddsediri/IterativePFN)]
- [Robust Outlier Rejection for 3D Registration with Variational Bayes](https://arxiv.org/pdf/2304.01514v1.pdf) [`registration`; [Github](https://github.com/Jiang-HB/VBReg)]
- [Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting](https://arxiv.org/pdf/2304.00467v1.pdf) [`registration`; [PyTorch](https://github.com/WHU-USI3DV/SGHR)]
- [3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds](https://arxiv.org/pdf/2304.00690v1.pdf) [`seg`; [PyTorch](https://github.com/xiaoaoran/SemanticSTF)]
- [RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving](https://arxiv.org/pdf/2301.10222.pdf) [`seg`; [Github](https://github.com/valeoai/rangevit)]
- [Understanding the Robustness of 3D Object Detection with Bird's-Eye-View Representations in Autonomous Driving](https://arxiv.org/pdf/2303.17297.pdf) [`det`]
- [NerVE: Neural Volumetric Edges for Parametric Curve Extraction from Point Cloud](https://arxiv.org/pdf/2303.16465.pdf) [`parametric curve`; [Project](https://dongdu3.github.io/projects/2023/NerVE/)]
- [LinK: Linear Kernel for LiDAR-based 3D Perception](https://arxiv.org/pdf/2303.16094.pdf) [`det`, `seg`; [Github](https://github.com/MCG-NJU/LinK)]
- [NeuralPCI: Spatio-temporal Neural Field for 3D Point Cloud Multi-frame Non-linear Interpolation](https://arxiv.org/pdf/2303.15126.pdf) [`interpolation`; [Github](https://github.com/ispc-lab/NeuralPCI)]
- [UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View](https://arxiv.org/pdf/2303.15083.pdf) [`det`; [PyTorch](https://github.com/megvii-research/CVPR2023-UniDistill)]
- [3D Video Object Detection with Learnable Object-Centric Global Optimization](https://arxiv.org/pdf/2303.15416.pdf) [`det`; [Github](https://github.com/jiaweihe1996/BA-Det)]
- [EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervision](https://arxiv.org/pdf/2303.15440.pdf) [`seg`; [PyTorch](https://github.com/JiahuiLei/EFEM)]
- [Collaboration Helps Camera Overtake LiDAR in 3D Detection](https://arxiv.org/pdf/2303.13560v1.pdf) [`det`; [Github](https://github.com/MediaBrain-SJTU/CoCa3D)]
- [Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration](https://arxiv.org/pdf/2303.13290v1.pdf) [`registration`; [Github](https://github.com/gfmei/UDPReg)]
- [MonoATT: Online Monocular 3D Object Detection with Adaptive Token Transformer](https://arxiv.org/pdf/2303.13018v1.pdf) [`det`]
- [FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer](https://arxiv.org/pdf/2301.08739.pdf) [`det`]
- [OcTr: Octree-based Transformer for 3D Object Detection](https://arxiv.org/pdf/2303.12621v1.pdf) [`det`]
- [Spherical Transformer for LiDAR-based 3D Recognition](https://arxiv.org/pdf/2303.12766v1.pdf) [`seg`, `det`; [PyTorch](https://github.com/dvlab-research/SphereFormer)]
- [Novel Class Discovery for 3D Point Cloud Semantic Segmentation](https://arxiv.org/pdf/2303.11610v1.pdf) [`seg`; [PyTorch](https://github.com/LuigiRiz/NOPS)]
- [3DQD: Generalized Deep 3D Shape Prior via Part-Discretized Diffusion Process](https://arxiv.org/pdf/2303.10406v1.pdf) [`generation`; [PyTorch](https://github.com/colorful-liyu/3DQD)]
- [Learning 3D Scene Priors with 2D Supervision](https://arxiv.org/pdf/2211.14157.pdf) [`layout`, `shape`; [Project](https://yinyunie.github.io/sceneprior-page/)]
- [Self-Supervised Learning for Multimodal Non-Rigid 3D Shape Matching](https://arxiv.org/pdf/2303.10971v1.pdf) [`non-rigid matching`; [PyTorch](https://github.com/dongliangcao/Self-Supervised-Multimodal-Shape-Matching)]
- [Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation](https://arxiv.org/pdf/2303.11203v1.pdf) [`seg`; [Github](https://github.com/l1997i/lim3d/)]
- [CAPE: Camera View Position Embedding for Multi-View 3D Object Detection](https://arxiv.org/pdf/2303.10209v1.pdf) [`det`; [Github](https://github.com/kaixinbear/CAPE)]
- [Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving](https://arxiv.org/pdf/2303.11040v1.pdf) [`det`; [Github](https://github.com/kkkcx/3D_Corruptions_AD)]
- [AeDet: Azimuth-invariant Multi-view 3D Object Detection](https://arxiv.org/pdf/2211.12501.pdf) [`det`; [PyTorch](https://github.com/fcjian/AeDet)]
- [VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking](https://arxiv.org/pdf/2303.11301v1.pdf) [`det`, `tracking`; [PyTorch](https://github.com/dvlab-research/VoxelNeXt)]
- [Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking](https://arxiv.org/pdf/2302.03802.pdf) [`tracking`; [Github](https://github.com/TRI-ML/PF-Track)]
- [Deep Graph-based Spatial Consistency for Robust Non-rigid Point Cloud Registration](https://arxiv.org/pdf/2303.09950v1.pdf) [`non-rigid registration`; [Github](https://github.com/qinzheng93/GraphSCNet)]
- [PEAL: Prior-Embedded Explicit Attention Learning for Low-Overlap Point Cloud Registration](https://openaccess.thecvf.com/content/CVPR2023/papers/Yu_PEAL_Prior-Embedded_Explicit_Attention_Learning_for_Low-Overlap_Point_Cloud_Registration_CVPR_2023_paper.pdf) [`registration`; [Github](https://github.com/Gardlin/PEAL)]
- [BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud Registration](https://openaccess.thecvf.com/content/CVPR2023/papers/Ao_BUFFER_Balancing_Accuracy_Efficiency_and_Generalizability_in_Point_Cloud_Registration_CVPR_2023_paper.pdf) [`registration`; [Github](https://github.com/aosheng1996/BUFFER)]
- [TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving](https://arxiv.org/pdf/2303.09998v1.pdf) [`autonomous driving`; [Github](https://github.com/MediaBrain-SJTU/TBP-Former)]
- [MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Driving](https://arxiv.org/pdf/2303.08600v1.pdf) [`seg`; [PyTorch](https://github.com/jialeli1/lidarseg3d)]
- [MSF: Motion-guided Sequential Fusion for Efficient 3D Object Detection from Point Cloud Sequences](https://arxiv.org/pdf/2303.08316v1.pdf) [`det`; [Github](https://github.com/skyhehe123/MSF)]
- [Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistency](https://arxiv.org/pdf/2303.08686v1.pdf) [`det`; [Github](https://github.com/weakmono3d/weakmono3d)]
- [Rotation-Invariant Transformer for Point Cloud Matching](https://arxiv.org/pdf/2303.08231v1.pdf) [`matching`]
- [Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fields](https://arxiv.org/pdf/2303.16482.pdf) [`rendering`]
- [Frequency-Modulated Point Cloud Rendering with Easy Editing](https://arxiv.org/pdf/2303.07596v1.pdf) [`rendering`; [PyTorch](https://github.com/yizhangphd/FreqPCR)]
- [Meta Architecure for Point Cloud Analysis](https://arxiv.org/pdf/2211.14462.pdf) [`seg`, `cls`; [PyTorch](https://github.com/linhaojia13/PointMetaBase)]
- [ULIP: Learning Unified Representation of Language, Image and Point Cloud for 3D Understanding](https://arxiv.org/pdf/2212.05171.pdf) [`cls`; [Github](https://github.com/salesforce/ULIP)]
- [Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis](https://arxiv.org/pdf/2303.08134v1.pdf) [`cls`, `seg`, `det`; [PyTorch](https://github.com/ZrrSkywalker/Point-NN)]
- [PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection](https://arxiv.org/pdf/2303.08129v1.pdf) [`det`; [PyTorch](https://github.com/BLVLab/PiMAE)]
- [SCPNet: Semantic Scene Completion on Point Cloud](https://arxiv.org/pdf/2303.06884v1.pdf) [`semantic scene completion`]
- [Uni3D: A Unified Baseline for Multi-dataset 3D Object Detection](https://arxiv.org/pdf/2303.06880v1.pdf) [`det`; [Github](https://github.com/PJLab-ADG/3DTrans)]
- [Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detection](https://arxiv.org/pdf/2303.05886v1.pdf) [`det`; [Github](https://github.com/PJLab-ADG/3DTrans)]
- [LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion](https://arxiv.org/pdf/2303.03595v1.pdf) [`det`; [Github](https://github.com/sankin97/LoGoNet)]
- [X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection](https://arxiv.org/pdf/2303.02203v1.pdf) [`det`]
- [Virtual Sparse Convolution for Multimodal 3D Object Detection](https://arxiv.org/pdf/2303.02314v1.pdf) [`det`; [PyTorch](https://github.com/hailanyi/VirConv)]
- [Unsupervised 3D Shape Reconstruction by Part Retrieval and Assembly](https://arxiv.org/pdf/2303.01999v1.pdf) [`reconstruction`]
- [ACL-SPC: Adaptive Closed-Loop system for Self-Supervised Point Cloud Completion](https://arxiv.org/pdf/2303.01979v1.pdf) [`completion`; [Github](https://github.com/Sangminhong/ACL-SPC_PyTorch)]
- [PointCert: Point Cloud Classification with Deterministic Certified Robustness Guarantees](https://arxiv.org/pdf/2303.01959v1.pdf) [`cls`]
- [Towards Domain Generalization for Multi-view 3D Object Detection in Bird-Eye-View](https://arxiv.org/pdf/2303.01686v1.pdf) [`det`]
- [Neural Intrinsic Embedding for Non-rigid Point Cloud Matching](https://arxiv.org/pdf/2303.01038v1.pdf) [`non-rigid matching`]
- [SBNet: a 3D Point Cloud Instance Segmentation Network with Instance-aware Sampling and Box-aware Dynamic Convolution](https://arxiv.org/pdf/2303.00246v1.pdf) [`seg`]
- [Multimodal Industrial Anomaly Detection via Hybrid Fusion](https://arxiv.org/pdf/2303.00601.pdf) [`anomaly detection`; [Github](https://github.com/nomewang/M3DM)]
- [ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformer](https://arxiv.org/pdf/2302.14435v1.pdf) [`completion`; [PyTorch](https://github.com/I2-Multimedia-Lab/ProxyFormer)]
- [Point Cloud Forecasting as a Proxy for 4D Occupancy Forecasting](https://arxiv.org/pdf/2302.13130.pdf) [`autonomous driving`; [PyTorch](https://github.com/tarashakhurana/4d-occ-forecasting)]
- [VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion](https://arxiv.org/pdf/2302.12251.pdf) [`autonomous driving`; [Github](https://github.com/NVlabs/VoxFormer)]
- [Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction](https://arxiv.org/pdf/2302.07817.pdf) [`autonomous driving`; [PyTorch](https://github.com/wzzheng/TPVFormer)]
- [CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIP](https://arxiv.org/pdf/2301.04926v1.pdf) [`pre-training`]
- [CLIP^2: Contrastive Language-Image-Point Pretraining from Real-World Point Cloud Data](https://arxiv.org/pdf/2303.12417v1.pdf) [`pre-training`]
- [ConQueR: Query Contrast Voxel-DETR for 3D Object Detection](https://arxiv.org/pdf/2212.07289.pdf) [`det`; [Github](https://github.com/poodarchu/ConQueR)]
- [Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders](https://arxiv.org/pdf/2212.06785.pdf) [`pre-training`; [Github](https://github.com/ZrrSkywalker/I2P-MAE)]
- [GD-MAE: Generative Decoder for MAE Pre-training on LiDAR Point Clouds](https://arxiv.org/pdf/2212.03010.pdf) [`pre-training`; [Github](https://github.com/Nightmare-n/GD-MAE)]
- [BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision](https://arxiv.org/pdf/2211.10439.pdf) [`autonomous driving`]
- [MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object Detection](https://arxiv.org/pdf/2209.03102.pdf) [`det`; [Github](https://github.com/SxJyJay/MSMDFusion)]
- [DETRs with Hybrid Matching](https://arxiv.org/pdf/2207.13080.pdf) [`det`; [Github](https://github.com/HDETR)]
- [LaserMix for Semi-Supervised LiDAR Semantic Segmentation](https://arxiv.org/pdf/2207.00026.pdf) [`seg`; [PyTorch](https://github.com/ldkong1205/LaserMix)]
- [PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection](https://arxiv.org/pdf/2205.11098.pdf) [`det`; [Github](https://github.com/RunpeiDong/PointDistiller)]
- [Anchor3DLane: Learning to Regress 3D Anchors for Monocular 3D Lane Detection](https://arxiv.org/pdf/2301.02371v1.pdf) [`lane det`]
- [PLA: Language-Driven Open-Vocabulary 3D Scene Understanding](https://arxiv.org/pdf/2211.16312.pdf) [`open-vocabulary`; [Github](https://github.com/CVMI-Lab/PLA)]
- AAAI
- [Context-Aware Transformer for 3D Point Cloud Automatic Annotation](https://arxiv.org/pdf/2303.14893.pdf) [`annotation`]
- [GAM : Gradient Attention Module of Optimization for Point Clouds Analysis](https://arxiv.org/pdf/2303.10543v1.pdf) [`seg`, `det`, `cls`; [PyTorch](https://github.com/hht1996ok/GAM)]
- [Parametric Surface Constrained Upsampler Network for Point Cloud](https://arxiv.org/pdf/2303.08240v1.pdf) [`upsampling`; [PyTorch](https://github.com/corecai163/PSCU)]
- [CRIN: Rotation-Invariant Point Cloud Analysis and Rotation Estimation via Centrifugal Reference Frame](https://arxiv.org/pdf/2303.03101v1.pdf) [`rotation invariance`]
- [PUPS: Point Cloud Unified Panoptic Segmentation](https://arxiv.org/pdf/2302.06185.pdf) [`seg`]
- [StereoDistill: Pick the Cream from LiDAR for Distilling Stereo-based 3D Object Detection](https://arxiv.org/pdf/2301.01615v1.pdf) [`det`]
- [Rethinking Rotation Invariance with Point Cloud Registration](https://arxiv.org/pdf/2301.00149v1.pdf) [`cls`, `seg`, `retrieval`; [PyTorch](https://github.com/Crane-YU/rethink_rotation)]
- [SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloud](https://arxiv.org/pdf/2212.02845.pdf) [`det`; [Github](https://github.com/yinjunbo/SSDA3D)]
- [CL3D: Unsupervised Domain Adaptation for Cross-LiDAR 3D Detection](https://arxiv.org/pdf/2212.00244.pdf) [`det`; [Github](https://github.com/4DVLab/CL3D)]
- [MGTANet: Encoding Sequential LiDAR Points Using Long Short-Term Motion-Guided Temporal Attention for 3D Object Detection](https://arxiv.org/pdf/2212.00442.pdf) [`det`; [PyTorch](https://github.com/HYjhkoh/MGTANet)]
- [Attention-based Depth Distillation with 3D-Aware Positional Encoding for Monocular 3D Object Detection](https://arxiv.org/pdf/2211.16779.pdf) [`det`; [Github](https://github.com/rockywind/ADD)]
- [NeAF: Learning Neural Angle Fields for Point Normal Estimation](https://arxiv.org/pdf/2211.16869.pdf) [`normal estimation`; [PyTorch](https://github.com/lisj575/NeAF/)]
- [Superpoint Transformer for 3D Scene Instance Segmentation](https://arxiv.org/pdf/2211.15766.pdf) [`seg`; [PyTorch](https://github.com/sunjiahao1999/SPFormer)]
- [Language-Assisted 3D Feature Learning for Semantic Scene Understanding](https://arxiv.org/pdf/2211.14091.pdf) [`det`, `seg`; [Github](https://github.com/Asterisci/Language-Assisted-3D)]
- [CasFusionNet: A Cascaded Network for Point Cloud Semantic Scene Completion by Dense Feature Fusion](https://arxiv.org/pdf/2211.13702.pdf) [`semantic scene completion`; [Github](https://github.com/JinfengX/CasFusionNet)]
- [SEFormer: Structure Embedding Transformer for 3D Object Detection](https://arxiv.org/pdf/2209.01745.pdf) [`det`]
- [Transformation-Equivariant 3D Object Detection for Autonomous Driving](https://arxiv.org/pdf/2211.11962.pdf) [`det`]
- [PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examples](https://arxiv.org/pdf/2211.12294.pdf) [`completion`]
- [GLT-T: Global-Local Transformer Voting for 3D Single Object Tracking in Point Clouds](https://arxiv.org/pdf/2211.10927.pdf) [`tracking`; [Github](https://github.com/haooozi/GLT-T)]
- [Normal Transformer: Extracting Surface Geometry from LiDAR Points Enhanced by Visual Semantics](https://arxiv.org/pdf/2211.10580.pdf) [`normal estimation`]
- [A Simple Baseline for Multi-Camera 3D Object Detection](https://arxiv.org/pdf/2208.10035.pdf) [`det`; [Github](https://github.com/zhangyp15/SimMOD)]
- [PolarFormer: Multi-camera 3D Object Detection with Polar Transformer](https://arxiv.org/pdf/2206.15398.pdf) [`det`; [PyTorch](https://github.com/fudan-zvg/PolarFormer)]
- [BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection](https://arxiv.org/pdf/2206.10092.pdf) [`det`; [PyTorch](https://github.com/Megvii-BaseDetection/BEVDepth)]
- [BEVStereo: Enhancing Depth Estimation in Multi-view 3D Object Detection with Dynamic Temporal Stereo](https://arxiv.org/pdf/2209.10248.pdf) [`det`; [PyTorch](https://github.com/Megvii-BaseDetection/BEVStereo)]
- Others
- [PointGPT: Auto-regressively Generative Pre-training from Point Clouds](https://arxiv.org/pdf/2305.11487.pdf) [`pre-training`; [Github](https://github.com/CGuangyan-BIT/PointGPT); NeurIPS]
- [Segment Anything in 3D with NeRFs](https://arxiv.org/pdf/2304.12308v1.pdf) [`seg`; [Github](https://github.com/Jumpat/SegmentAnythingin3D); NeurIPS]
- [SAM3D: Segment Anything in 3D Scenes](https://arxiv.org/pdf/2306.03908.pdf) [`seg`; [PyTorch](https://github.com/Pointcept/SegmentAnything3D); NeurIPS]
- [Segment Any Point Cloud Sequences by Distilling Vision Foundation Models](https://arxiv.org/pdf/2306.09347.pdf) [`seg`; [Github](https://github.com/youquanl/Segment-Any-Point-Cloud); NeurIPS]
- [Real3D-AD: A Dataset of Point Cloud Anomaly Detection](https://arxiv.org/pdf/2309.13226.pdf) [`det`; [Github](https://github.com/M-3LAB/Real3D-AD); NeurIPS]
- [AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset](https://arxiv.org/pdf/2306.00612.pdf) [`pre-training`; [PyTorch](https://github.com/PJLab-ADG/3DTrans); NeurIPS]
- [Explore In-Context Learning for 3D Point Cloud Understanding](https://arxiv.org/pdf/2306.08659.pdf) [`in-context learning`; [Github](https://github.com/fanglaosi/Point-In-Context); NeurIPS]
- [E2PNet: Event to Point Cloud Registration with Spatio-Temporal Representation Learning](https://arxiv.org/pdf/2311.18433.pdf) [`registration`; NeurIPS]
- [SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation](https://arxiv.org/pdf/2310.17359.pdf) [`pose estimation`; [PyTorch](https://github.com/Jiang-HB/DiffusionReg); NeurIPS]
- [Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariance](https://arxiv.org/pdf/2305.16314.pdf) [`seg`; NeurIPS]
- [All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation](https://arxiv.org/pdf/2305.15832.pdf) [`seg`; NeurIPS]
- [DiffComplete: Diffusion-based Generative 3D Shape Completion](https://arxiv.org/pdf/2306.16329.pdf) [`completion`; [Project](https://ruihangchu.com/diffcomplete.html); NeurIPS]
- [DORT: Modeling Dynamic Objects in Recurrent for Multi-Camera 3D Object Detection and Tracking](https://arxiv.org/pdf/2303.16628.pdf) [`det`, `tracking`; [Github](https://github.com/SmartBot-PJLab/DORT); CoRL]
- [SUIT: Learning Significance-guided Information for 3D Temporal Detection](https://arxiv.org/pdf/2307.01807.pdf) [`det`; IROS]
- [Sparse Dense Fusion for 3D Object Detection](https://arxiv.org/pdf/2304.04179v1.pdf) [`det`; IROS]
- [PANet: LiDAR Panoptic Segmentation with Sparse Instance Proposal and Aggregation](https://arxiv.org/pdf/2306.15348.pdf) [`seg`; [PyTorch](https://github.com/Jieqianyu/PANet); IROS]
- [SSC-RS: Elevate LiDAR Semantic Scene Completion with Representation Separation and BEV Fusion](https://arxiv.org/pdf/2306.15349.pdf) [`semantic scene completion`; [PyTorch](https://github.com/Jieqianyu/SSC-RS); IROS]
- [ElC-OIS: Ellipsoidal Clustering for Open-World Instance Segmentation on LiDAR Data](https://arxiv.org/pdf/2303.04351v1.pdf) [`seg`; [Github](https://github.com/nubot-nudt/ElC-OIS); IROS]
- [InsMOS: Instance-Aware Moving Object Segmentation in LiDAR Data](https://arxiv.org/pdf/2303.03909v1.pdf) [`seg`; [Github](https://github.com/nubot-nudt/InsMOS); IROS]
- [Stable and Consistent Prediction of 3D Characteristic Orientation via Invariant Residual Learning](https://arxiv.org/pdf/2306.11406.pdf) [`analysis`; ICML]
- [VectorMapNet: End-to-end Vectorized HD Map Learning](https://arxiv.org/pdf/2206.08920.pdf) [`autonomous driving`; [Github](https://github.com/Tsinghua-MARS-Lab/vectormapnet); ICML]
- [STTracker: Spatio-Temporal Tracker for 3D Single Object Tracking](https://arxiv.org/pdf/2306.17440.pdf) [`det`; RAL]
- [Concavity-Induced Distance for Unoriented Point Cloud Decomposition](https://arxiv.org/pdf/2306.11051.pdf) [`analysis`; [Project](https://ai4ce.github.io/CID/); RAL]
- [Energy-based Detection of Adverse Weather Effects in LiDAR Data](https://arxiv.org/pdf/2305.16129.pdf) [`autonomous driving`; [Github](https://github.com/aldipiroli/semantic_spray_dataset); RAL]
- [Multi-modal Streaming 3D Object Detection](https://arxiv.org/pdf/2209.04966.pdf) [`det`; RAL]
- [You Only Label Once: 3D Box Adaptation From Point Cloud to Image With Semi-Supervised Learning](https://arxiv.org/pdf/2211.09302.pdf) [`det`; RAL]
- [Prototype Adaption and Projection for Few- and Zero-shot 3D Point Cloud Semantic Segmentation](https://arxiv.org/pdf/2305.14335.pdf) [`seg`; [Github](https://github.com/heshuting555/PAP-FZS3D); TIP]
- [APP-Net: Auxiliary-point-based Push and Pull Operations for Efficient Point Cloud Classification](https://arxiv.org/pdf/2205.00847.pdf) [`cls`; [PyTorch](https://github.com/MCG-NJU/APP-Net); TIP]
- [OBMO: One Bounding Box Multiple Objects for Monocular 3D Object Detection](https://arxiv.org/pdf/2212.10049.pdf) [`det`; [Github](https://github.com/mrsempress/OBMO); TIP]
- [OctFormer: Octree-based Transformers for 3D Point Clouds](https://arxiv.org/pdf/2305.03045.pdf) [`seg`, `det`; [Github](https://github.com/octree-nn/octformer); TOG]
- [Point Cloud Registration-Driven Robust Feature Matching for 3D Siamese Object Tracking](https://arxiv.org/pdf/2209.06395.pdf) [`tracking`; TNNLS]
- [Full Transformer Framework for Robust Point Cloud Registration with Deep Information Interaction](https://arxiv.org/pdf/2112.09385.pdf) [`registration`; [Github](https://github.com/CGuangyan-BIT/DIT); TNNLS]
- [CVTNet: A Cross-View Transformer Network for Place Recognition Using LiDAR Data](https://arxiv.org/pdf/2302.01665.pdf) [`place recognition`; [Github](https://github.com/BIT-MJY/CVTNet); TII]
- [PowerBEV: A Powerful Yet Lightweight Framework for Instance Prediction in Bird's-Eye View](https://arxiv.org/pdf/2306.10761.pdf) [`autonomous driving`; [PyTorch](https://github.com/EdwardLeeLPZ/PowerBEV); IJCAI]
- [APR: Online Distant Point Cloud Registration Through Aggregated Point Cloud Reconstruction](https://arxiv.org/pdf/2305.02893.pdf) [`registration`; [Github](https://github.com/liuQuan98/APR); IJCAI]
- [OSP2B: One-Stage Point-to-Box Network for 3D Siamese Tracking](https://arxiv.org/pdf/2304.11584v1.pdf) [`tracking`; IJCAI]
- [Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-training](https://arxiv.org/pdf/2302.14007.pdf) [`pre-training`; IJCAI]
- [A Closer Look at Few-Shot 3D Point Cloud Classification](https://arxiv.org/pdf/2303.18210v1.pdf) [`cls`; [Github](https://github.com/cgye96/A_Closer_Look_At_3DFSL); IJCV]
- [PointNorm: Normalization is All You Need for Point Cloud Analysis](https://arxiv.org/pdf/2207.06324.pdf) [`cls`, `seg`; [Github](https://github.com/ShenZheng2000/PointNorm-for-Point-Cloud-Analysis); IJCNN]
- [HybridPoint: Point Cloud Registration Based on Hybrid Point Sampling and Matching](https://arxiv.org/pdf/2303.16526.pdf) [`registration`; [Github](https://github.com/liyih/HybridPoint); ICME]
- [Variational Relational Point Completion Network for Robust 3D Classification](https://arxiv.org/pdf/2304.09131v1.pdf) [`completion`; TPAMI]
- [CP3: Unifying Point Cloud Completion by Pretrain-Prompt-Predict Paradigm](https://arxiv.org/pdf/2207.05359.pdf) [`completion`; TPAMI]
- [Fast and Robust Non-Rigid Registration Using Accelerated Majorization-Minimization](https://arxiv.org/pdf/2206.03410.pdf) [`registration`, `non-rigid`; [Github](https://github.com/yaoyx689/AMM_NRR); TPAMI]
- [RoReg: Pairwise Point Cloud Registration with Oriented Descriptors and Local Rotations](https://ieeexplore.ieee.org/abstract/document/10044259) [`registration`; [PyTorch](https://github.com/HpWang-whu/RoReg); TPAMI]
- [AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformers](https://arxiv.org/pdf/2301.04545v1.pdf) [`completion`; TPAMI]
- [Super Sparse 3D Object Detection](https://arxiv.org/pdf/2301.02562.pdf) [`det`; [PyTorch](https://github.com/tusen-ai/SST); TPAMI]
- [AGConv: Adaptive Graph Convolution on 3D Point Clouds](https://arxiv.org/pdf/2206.04665.pdf) [`cls`, `seg`; [PyTorch](https://github.com/hrzhou2/AdaptConv-master); TPAMI]
- [Analogy-Forming Transformers for Few-Shot 3D Parsing](https://arxiv.org/pdf/2304.14382v1.pdf) [`seg`; [Project](https://analogicalnets.github.io); ICLR]
- [Joint 2D-3D multi-task scene understanding on Cityscapes-3D: 3D detection, segmentation, and depth estimation](https://openreview.net/pdf?id=-CwPopPJda) [`seg`, `det`, `depth estimation`; [PyTorch](https://github.com/prismformore/Multi-Task-Transformer/tree/main/TaskPrompter); ICLR]
- [CircNet: Meshing 3D Point Clouds with Circumcenter Detection](https://arxiv.org/pdf/2301.09253.pdf) [`triangulation`; [Github](https://github.com/Ruitao-L/CircNet); ICLR]
- [BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection](https://arxiv.org/pdf/2211.09386.pdf) [`det`; [Github](https://github.com/zehuichen123/BEVDistill); ICLR]
- [Bidirectional Propagation for Cross-Modal 3D Object Detection](https://arxiv.org/pdf/2301.09077.pdf) [`det`; [PyTorch](https://github.com/Eaphan/BiProDet); ICLR]
- [Exploring Active 3D Object Detection from a Generalization Perspective](https://arxiv.org/pdf/2301.09249.pdf) [`det`; [PyTorch](https://github.com/Luoyadan/CRB-active-3Ddet); ICLR]
- [DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection](https://arxiv.org/pdf/2207.10909.pdf) [`det`; ICLR]
- [DDS3D: Dense Pseudo-Labels with Dynamic Threshold for Semi-Supervised 3D Object Detection](https://arxiv.org/pdf/2303.05079v1.pdf) [`det`; [Github](https://github.com/hust-jy/DDS3D); ICRA]
- [Are All Point Clouds Suitable for Completion? Weakly Supervised Quality Evaluation Network for Point Cloud Completion](https://arxiv.org/pdf/2303.01804v1.pdf) [`completion`; ICRA]
- [A Unified BEV Model for Joint Learning of 3D Local Features and Overlap Estimation](https://arxiv.org/pdf/2302.14511v1.pdf) [`registration`; ICRA]
- [LODE: Locally Conditioned Eikonal Implicit Scene Completion from Sparse LiDAR](https://arxiv.org/pdf/2302.14052.pdf) [`completion`; [PyTorch](https://github.com/AIR-DISCOVER/LODE); ICRA]
- [DuEqNet: Dual-Equivariance Network in Outdoor 3D Object Detection for Autonomous Driving](https://arxiv.org/pdf/2302.13577.pdf) [`det`; ICRA]
- [Few-Shot Point Cloud Semantic Segmentation via Contrastive Self-Supervision and Multi-Resolution Attention](https://arxiv.org/pdf/2302.10501.pdf) [`seg`; ICRA]
- [MVFusion: Multi-View 3D Object Detection with Semantic-aligned Radar and Camera Fusion](https://arxiv.org/pdf/2302.10511.pdf) [`det`; ICRA]
- [MonoPGC: Monocular 3D Object Detection with Pixel Geometry Contexts](https://arxiv.org/pdf/2302.10549.pdf) [`det`; ICRA]
- [SCARP: 3D Shape Completion in ARbitrary Poses for Improved Grasping](https://arxiv.org/pdf/2301.07213v1.pdf) [`completion`; [PyTorch](https://github.com/vanhalen42/SCARP); ICRA]
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://arxiv.org/pdf/2205.13542.pdf) [`autonomous driving`; [PyTorch](https://github.com/mit-han-lab/bevfusion); ICRA]
- [CrossDTR: Cross-view and Depth-guided Transformers for 3D Object Detection](https://arxiv.org/pdf/2209.13507.pdf) [`det`; [Github](https://github.com/sty61010/CrossDTR); ICRA]
- [ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via Regularized Domain Concatenation](https://arxiv.org/pdf/2111.15242.pdf) [`seg`, `unsupervised domain adaptation`; [Github](https://github.com/ldkong1205/ConDA); ICRA]
- [Mask3D: Mask Transformer for 3D Semantic Instance Segmentation](https://arxiv.org/pdf/2210.03105.pdf) [`seg`; ICRA]
- [STD: Stable Triangle Descriptor for 3D place recognition](https://arxiv.org/pdf/2209.12435.pdf) [`place recognition`; [Github](https://github.com/hku-mars/STD); ICRA]
- [MonoEdge: Monocular 3D Object Detection Using Local Perspectives](https://arxiv.org/pdf/2301.01802v1.pdf) [`det`; WACV]
- [Far3Det: Towards Far-Field 3D Detection](https://arxiv.org/pdf/2211.13858.pdf) [`det`; WACV]
- [Centroid Distance Keypoint Detector for Colored Point Clouds](https://arxiv.org/pdf/2210.01298.pdf) [`keypoint`; [Github](https://github.com/UCR-Robotics/CED_Detector); WACV]
- [NeuralBF: Neural Bilateral Filtering for Top-down Instance Segmentation on Point Clouds](https://arxiv.org/pdf/2207.09978.pdf) [`seg`; [Project](https://neuralbf.github.io); WACV]
- [Anomaly Detection in 3D Point Clouds using Deep Geometric Descriptors](https://arxiv.org/pdf/2202.11660.pdf) [`anomaly detection`; WACV]
- [SUG: Single-dataset Unified Generalization for 3D Point Cloud Classification](https://arxiv.org/pdf/2305.09160.pdf) [`cls`; [PyTorch](https://github.com/SiyuanHuang95/SUG); ACM MM]
- [Moby: Empowering 2D Models for Efficient Point Cloud Analytics on the Edge](https://arxiv.org/pdf/2302.09221.pdf) [`det`; ACM MM]
- [TR3D: Towards Real-Time Indoor 3D Object Detection](https://arxiv.org/pdf/2302.02858.pdf) [`det`; [PyTorch](https://github.com/SamsungLabs/tr3d); ICIP]
- [MS3D: Leveraging Multiple Detectors for Unsupervised Domain Adaptation in 3D Object Detection](https://arxiv.org/pdf/2304.02431v1.pdf) [`det`; [PyTorch](https://github.com/darrenjkt/MS3D); TITS]
- arXiv
- [DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation](https://arxiv.org/pdf/2307.01831.pdf) [`generation`; [Github](https://github.com/DiT-3D/DiT-3D)]
- [Frame Fusion with Vehicle Motion Prediction for 3D Object Detection](https://arxiv.org/pdf/2306.10699.pdf) [`det`]
- [UniOcc: Unifying Vision-Centric 3D Occupancy Prediction with Geometric and Semantic Rendering](https://arxiv.org/pdf/2306.09117.pdf) [`occupancy prediction`]
- [SAM3D: Zero-Shot 3D Object Detection via Segment Anything Model](https://arxiv.org/pdf/2306.02245.pdf) [`det`; [PyTorch](https://github.com/DYZhang09/SAM3D)]
- [Collect-and-Distribute Transformer for 3D Point Cloud Analysis](https://arxiv.org/pdf/2306.01257.pdf) [`cls`, `seg`; [PyTorch](https://github.com/haibo-qiu/CDFormer)]
- [BEV-IO: Enhancing Bird's-Eye-View 3D Detection with Instance Occupancy](https://arxiv.org/pdf/2305.16829.pdf) [`det`]
- [SAD: Segment Any RGBD](https://arxiv.org/pdf/2305.14207.pdf) [`seg`; [PyTorch](https://github.com/Jun-CEN/SegmentAnyRGBD)]
- [Real-Aug: Realistic Scene Synthesis for LiDAR Augmentation in 3D Object Detection](https://arxiv.org/pdf/2305.12853.pdf) [`augmentation`]
- [Multi-Modal 3D Object Detection by Box Matching](https://arxiv.org/pdf/2305.07713.pdf) [`det`; [Github](https://github.com/happinesslz/FBMNet)]
- [ContrastMotion: Self-supervised Scene Motion Learning for Large-Scale LiDAR Point Clouds](https://arxiv.org/pdf/2304.12589v1.pdf) [`scene motion`]
- [MetaBEV: Solving Sensor Failures for BEV Detection and Map Segmentation](https://arxiv.org/pdf/2304.09801v1.pdf) [`det`, `seg`; [Github](https://github.com/ChongjianGE/MetaBEV)]
- [3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining](https://arxiv.org/pdf/2304.06911v1.pdf) [`pre-training`]
- [Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding](https://arxiv.org/pdf/2304.06906v1.pdf) [`seg`, `det`; [Github](https://github.com/microsoft/Swin3D)]
- [RoboBEV: Towards Robust Bird's Eye View Perception under Corruptions](https://arxiv.org/pdf/2304.06719v1.pdf) [`autonomous driving`; [Github](https://github.com/Daniel-xsy/RoboBEV)]
- [BEVStereo++: Accurate Depth Estimation in Multi-view 3D Object Detection via Dynamic Temporal Stereo](https://arxiv.org/pdf/2304.04185v1.pdf) [`det`]
- [VPFusion: Towards Robust Vertical Representation Learning for 3D Object Detection](https://arxiv.org/pdf/2304.02867v1.pdf) [`det`]
- [Geometric-aware Pretraining for Vision-centric 3D Object Detection](https://arxiv.org/pdf/2304.03105v1.pdf) [`det`; [PyTorch](https://github.com/OpenDriveLab/BEVPerception-Survey-Recipe)]
- [VoxelFormer: Bird's-Eye-View Feature Generation based on Dual-view Attention for Multi-view 3D Object Detection](https://arxiv.org/pdf/2304.01054v1.pdf) [`det`; [PyTorch](https://github.com/Lizhuoling/VoxelFormer-public)]
- [EA-BEV: Edge-aware Bird' s-Eye-View Projector for 3D Object Detection](https://arxiv.org/pdf/2303.17895v1.pdf) [`det`; [Github](https://github.com/hht1996ok/EA-BEV)]
- [IC-FPS: Instance-Centroid Faster Point Sampling Module for 3D Point-base Object Detection](https://arxiv.org/pdf/2303.17921v1.pdf) [`det`; [Github](https://github.com/hht1996ok/IC-FPS)]
- [APPT : Asymmetric Parallel Point Transformer for 3D Point Cloud Understanding](https://arxiv.org/pdf/2303.17815v1.pdf) [`seg`, `cls`]
- [BEVFusion4D: Learning LiDAR-Camera Fusion Under Bird's-Eye-View via Cross-Modality Guidance and Temporal Aggregation](https://arxiv.org/pdf/2303.17099.pdf) [`det`]
- [ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Box](https://arxiv.org/pdf/2303.15334.pdf) [`tracking`; [Github](https://github.com/ifzhang/ByteTrack-V2)]
- [3D Data Augmentation for Driving Scenes on Camera](https://arxiv.org/pdf/2303.10340v1.pdf) [`autonomous driving`]
- [Vehicle-Infrastructure Cooperative 3D Object Detection via Feature Flow Prediction](https://arxiv.org/pdf/2303.10552v1.pdf) [`autonomous driving`; [PyTorch](https://github.com/haibao-yu/FFNet-VIC3D)]
- [A Simple Attempt for 3D Occupancy Estimation in Autonomous Driving](https://arxiv.org/pdf/2303.10076v1.pdf) [`autonomous driving`; [Github](https://github.com/GANWANSHUI/SimpleOccupancy)]
- [DiffBEV: Conditional Diffusion Model for Bird's Eye View Perception](https://arxiv.org/pdf/2303.08333v1.pdf) [`seg`, `det`; [PyTorch](https://github.com/JiayuZou2020/DiffBEV)]
- [GeoSpark: Sparking up Point Cloud Segmentation with Geometry Clue](https://arxiv.org/pdf/2303.08274v1.pdf) [`seg`]
- [Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perception](https://arxiv.org/pdf/2303.05970v1.pdf) [`autonomous driving`]
- [OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion](https://arxiv.org/pdf/2302.13540.pdf) [`autonomous driving`; [PyTorch](https://github.com/megvii-research/OccDepth)]
- [DA-BEV: Depth Aware BEV Transformer for 3D Object Detection](https://arxiv.org/pdf/2302.13002.pdf) [`det`]
- [Pillar R-CNN for Point Cloud 3D Object Detection](https://arxiv.org/pdf/2302.13301.pdf) [`det`]
- [General Rotation Invariance Learning for Point Clouds via Weight-Feature Alignment](https://arxiv.org/pdf/2302.09907.pdf) [`cls`, `seg`, `det`]
- [AOP-Net: All-in-One Perception Network for Joint LiDAR-based 3D Object Detection and Panoptic Segmentation](https://arxiv.org/pdf/2302.00885.pdf) [`det`, `seg`]
- [On the Adversarial Robustness of Camera-based 3D Object Detection](https://arxiv.org/pdf/2301.10766.pdf) [`det`]
- [OA-BEV: Bringing Object Awareness to Bird’s-Eye-View Representation for Multi-Camera 3D Object Detection](https://arxiv.org/pdf/2301.05711v1.pdf) [`det`]
- [SAT: Size-Aware Transformer for 3D Point Cloud Semantic Segmentation](https://arxiv.org/pdf/2301.06869v1.pdf) [`seg`]
- [FSD V2: Improving Fully Sparse 3D Object Detection with Virtual Voxels](https://arxiv.org/pdf/2308.03755.pdf) [`det`; [PyTorch](https://github.com/tusen-ai/SST)]
- [Overlap Bias Matching is Necessary for Point Cloud Registration](https://arxiv.org/pdf/2308.09364.pdf) [`registration`]
- [One-Nearest Neighborhood Guides Inlier Estimation for Unsupervised Point Cloud Registration](https://arxiv.org/pdf/2307.14019.pdf) [`registration`]
- [Direct Superpoints Matching for Fast and Robust Point Cloud Registration](https://arxiv.org/pdf/2307.01362.pdf) [`registration`]
## 2022
- ECCV
- [PCR-CG: Point Cloud Registration via Color and Geometry](https://arxiv.org/pdf/2302.14418v1.pdf) [`registration`; [PyTorch](https://github.com/Gardlin/PCR-CG)]
- [SPE-Net: Boosting Point Cloud Analysis via Rotation Robustness Enhancement](https://arxiv.org/pdf/2211.08250.pdf) [`cls`, `seg`; [PyTorch](https://github.com/ZhaofanQiu/SPE-Net)]
- [Image2Point: 3D Point-Cloud Understanding withPretrained 2D ConvNets](https://arxiv.org/pdf/2106.04180.pdf) [`cls`, `seg`; [Github](https://github.com/chenfengxu714/image2point)]
- [Cross-Modality Knowledge Distillation Network for Monocular 3D Object Detection](https://arxiv.org/pdf/2211.07171.pdf) [`det`; [PyTorch](https://github.com/Cc-Hy/CMKD)]
- [LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation](https://arxiv.org/pdf/2211.05997.pdf) [`seg`; [Github](https://github.com/hzykent/LiDAL)]
- [DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detection](https://arxiv.org/pdf/2203.09510v1.pdf) [`det`; [Github](https://github.com/Divadi/DetMatch)]
- [Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection](https://arxiv.org/pdf/2210.09615.pdf) [`det`]
- [Improving the Intra-class Long-tail in 3D Detection via Rare Example Mining](https://arxiv.org/pdf/2210.08375.pdf) [`det`]
- [CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection](https://arxiv.org/pdf/2210.09267.pdf) [`det`]
- [LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds](https://arxiv.org/pdf/2210.08064.pdf) [`seg`]
- [Autoregressive Uncertainty Modeling for 3D Bounding Box Prediction](https://arxiv.org/pdf/2210.07424.pdf) [`det`; [PyTorch](https://github.com/wyndwarrior/autoregressive-bbox)]
- [SWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds](https://arxiv.org/pdf/2210.07372.pdf) [`det`]
- [LidarNAS: Unifying and Searching Neural Architectures for 3D Point Clouds](https://arxiv.org/pdf/2210.05018.pdf) [`NAS`]
- [FBNet: Feedback Network for Point Cloud Completion](https://arxiv.org/pdf/2210.03974.pdf) [`completion`; [PyTorch](https://github.com/hikvision-research/3DVision/)]
- [INT: Towards Infinite-frames 3D Detection with An Efficient Framework](https://arxiv.org/pdf/2209.15215.pdf) [`det`]
- [MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection](https://arxiv.org/pdf/2205.05979.pdf) [`det`; [Github](https://github.com/open-mmlab/OpenPCDet)]
- [PointInst3D: Segmenting 3D Instances by Points](https://arxiv.org/pdf/2204.11402.pdf) [`seg`; [Github](https://github.com/tonghe90/PointInst3D)]
- [PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detection](https://arxiv.org/pdf/2205.07403.pdf) [`det`; [PyTorch](https://github.com/agent-sgs/PillarNet)]
- [GitNet: Geometric Prior-based Transformation for Birds-Eye-View Segmentation](https://arxiv.org/pdf/2204.07733.pdf) [`autonomous driving`]
- [Geodesic-Former: a Geodesic-Guided Few-shot 3D Point Cloud Instance Segmenter](https://arxiv.org/pdf/2207.10859.pdf) [`seg`; [Github](https://github.com/VinAIResearch/GeoFormer)]
- [Multimodal Transformer for Automatic 3D Annotation and Object Detection](https://arxiv.org/pdf/2207.09805.pdf) [`det`; [PyTorch](https://github.com/Cliu2/MTrans)]
- [Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes](https://arxiv.org/pdf/2206.01203.pdf) [`seg`; [PyTorch](https://github.com/jchibane/Box2Mask)]
- [Online Segmentation of LiDAR Sequences: Dataset and Algorithm](https://arxiv.org/pdf/2206.08194.pdf) [`seg`; [PyTorch](https://github.com/romainloiseau/Helix4D)]
- [SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse views](https://arxiv.org/pdf/2206.05737.pdf) [`reconstruction`; [PyTorch](https://github.com/xxlong0/SparseNeuS)]
- [Language-Grounded Indoor 3D Semantic Segmentation in the Wild](https://arxiv.org/pdf/2204.07761.pdf) [`seg`; [PyTorch](https://github.com/RozDavid/LanguageGroundedSemseg)]
- [CenterFormer: Center-based Transformer for 3D Object Detection](https://arxiv.org/pdf/2209.05588.pdf) [`det`; [Github](https://github.com/TuSimple/centerformer)]
- [Learning to Generate Realistic LiDAR Point Clouds](https://arxiv.org/pdf/2209.03954.pdf) [`generation`; [Project](https://www.zyrianov.org/lidargen/)]
- [PointCLM: A Contrastive Learning-based Framework for Multi-instance Point Cloud Registration](https://arxiv.org/pdf/2209.00219.pdf) [`registration`; [Github](https://github.com/phdymz/PointCLM)]
- [SimpleRecon: 3D Reconstruction Without 3D Convolutions](https://arxiv.org/pdf/2208.14743.pdf) [`reconstruction`; [Project](https://nianticlabs.github.io/simplerecon/)]
- [Improving RGB-D Point Cloud Registration by Learning Multi-scale Local Linear Transformation](https://arxiv.org/pdf/2208.14893.pdf) [`registration`; [Github](https://github.com/514DNA/LLT)]
- [Masked Discrimination for Self-Supervised Learning on Point Clouds](https://arxiv.org/pdf/2203.11183v1.pdf) [`self-supervised`; [PyTorch](https://github.com/haotian-liu/MaskPoint)]
- [MORE: Multi-Order RElation Mining for Dense Captioning in 3D Scenes](https://arxiv.org/abs/2203.05203) [`dense captioning`; [Github](https://github.com/SxJyJay/MORE)]
- [Objects Can Move: 3D Change Detection by Geometric Transformation Constistency](https://arxiv.org/pdf/2208.09870.pdf) [`change detection`; [Github](https://github.com/katadam/ObjectsCanMove)]
- [PointTree: Transformation-Robust Point Cloud Encoder with Relaxed K-D Trees](https://arxiv.org/pdf/2208.05962.pdf) [`cls`, `seg`; [PyTorch](https://github.com/immortalCO/PointTree)]
- [diffConv: Analyzing Irregular Point Clouds with an Irregular View](https://arxiv.org/pdf/2111.14658.pdf) [`cls`, `seg`; [PyTorch](https://github.com/mmmmimic/diffConvNet)]
- [SLiDE: Self-supervised LiDAR De-snowing through Reconstruction Difficulty](https://arxiv.org/pdf/2208.04043.pdf) [`de-snowing`]
- [Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph](https://arxiv.org/pdf/2208.03624.pdf) [`det`; [PyTorch](https://github.com/Nightmare-n/GraphRCNN)]
- [Point Primitive Transformer for Long-Term 4D Point Cloud Video Understanding](https://arxiv.org/pdf/2208.00281.pdf) [`4D`]
- [Few-shot Single-view 3D Reconstruction with Memory Prior Contrastive Network](https://arxiv.org/pdf/2208.00183.pdf) [`reconstruction`]
- [NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors](https://arxiv.org/pdf/2206.13597.pdf) [`reconstruction`; [Project](https://jiepengwang.github.io/NeuRIS/)]
- [PolarMOT: How Far Can Geometric Relations Take Us in 3D Multi-Object Tracking?](https://arxiv.org/pdf/2208.01957.pdf) [`tracking`]
- [SpOT: Spatiotemporal Modeling for 3D Object Tracking](https://arxiv.org/pdf/2207.05856.pdf) [`tracking`; [PyTorch](https://github.com/coltonstearns/SpOT)]
- [MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud](https://arxiv.org/pdf/2207.14268.pdf) [`representation`]
- [Large-displacement 3D Object Tracking with Hybrid Non-local Optimization](https://arxiv.org/pdf/2207.12620.pdf) [`tracking`; [Github](https://github.com/cvbubbles/nonlocal-3dtracking)]
- [SimpleTrack: Understanding and Rethinking 3D Multi-object Tracking](https://arxiv.org/pdf/2111.09621.pdf) [`track`; [Github](https://github.com/TuSimple/SimpleTrack)]
- [ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection](https://arxiv.org/pdf/2207.12654.pdf) [`det`; [Github](https://github.com/yinjunbo/ProposalContrast)]
- [Semi-supervised 3D Object Detection with Proficient Teachers](https://arxiv.org/pdf/2207.12655.pdf) [`det`; [Github](https://github.com/yinjunbo/ProficientTeachers)]
- [Monocular 3D Object Detection with Depth from Motion](https://arxiv.org/pdf/2207.12988.pdf) [`det`; [PyTorch](https://github.com/Tai-Wang/Depth-from-Motion)]
- [GraphFit: Learning Multi-scale Graph-Convolutional Representation for Point Cloud Normal Estimation](https://arxiv.org/pdf/2207.11484.pdf) [`normal estimation`; [PyTorch](https://github.com/UestcJay/GraphFit)]
- [PatchRD: Detail-Preserving Shape Completion by Learning Patch Retrieval and Deformation](https://arxiv.org/pdf/2207.11790.pdf) [`completion`; [PyTorch](https://github.com/GitBoSun/PatchRD)]
- [Label-Guided Auxiliary Training Improves 3D Object Detector](https://arxiv.org/pdf/2207.11753.pdf) [`det`; [Github](https://github.com/FabienCode/LG3D)]
- [Salient Object Detection for Point Clouds](https://arxiv.org/pdf/2207.11889.pdf) [`det`; [Code](https://git.openi.org.cn/OpenPointCloud/PCSOD)]
- [3D Siamese Transformer Network for Single Object Tracking on Point Clouds](https://arxiv.org/pdf/2207.11995.pdf) [`tracking`; [Github](https://github.com/fpthink/STNet)]
- [Point Cloud Compression with Sibling Context and Surface Priors](https://arxiv.org/pdf/2205.00760.pdf) [`compression`; [PyTorch](https://github.com/zlichen/PCC-S)]
- [SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds with 1000× Fewer Labels](https://arxiv.org/pdf/2104.04891.pdf) [`seg`; [Tensorflow](https://github.com/QingyongHu/SQN)]
- [PointMixer: MLP-Mixer for Point Cloud Understanding](https://arxiv.org/pdf/2111.11187.pdf) [`seg`, `cls`, `reconstruction`; [PyTorch](https://github.com/LifeBeyondExpectations/ECCV22-PointMixer)]
- [DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection](https://arxiv.org/pdf/2207.10758.pdf) [`det`, `monocular`; [PyTorch](https://github.com/abhi1kumar/DEVIANT)]
- [Dynamic 3D Scene Analysis by Point Cloud Accumulation](https://arxiv.org/pdf/2207.12394.pdf) [`accumulation`; [PyTorch](https://github.com/prs-eth/PCAccumulation)]
- [MeshMAE: Masked Autoencoders for 3D Mesh Data Analysis](https://arxiv.org/pdf/2207.10228.pdf) [`self-supervised`]
- [SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformer](https://arxiv.org/pdf/2207.10315.pdf) [`completion`; [PyTorch](https://github.com/hrzhou2/seedformer)]
- [Unsupervised Deep Multi-Shape Matching](https://arxiv.org/pdf/2207.09610.pdf) [`matching`]
- [Monocular 3D Object Reconstruction with GAN Inversion](https://arxiv.org/pdf/2207.10061.pdf) [`reconstruction`; [PyTorch](https://github.com/junzhezhang/mesh-inversion)]
- [CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation](https://arxiv.org/pdf/2207.09778.pdf) [`seg`; [PyTorch](https://github.com/saltoricristiano/cosmix-uda)]
- [GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation](https://arxiv.org/pdf/2207.09763.pdf) [`seg`; [PyTorch](https://github.com/saltoricristiano/gipso-sfouda)]
- [Densely Constrained Depth Estimator for Monocular 3D Object Detection](https://arxiv.org/pdf/2207.10047.pdf) [`det`, `monocular`; [PyTorch](https://github.com/BraveGroup/DCD)]
- [SuperLine3D: Self-supervised Line Segmentation and Description for LiDAR Point Cloud](https://arxiv.org/pdf/2208.01925.pdf) [`registration`; [Tensorflow](https://github.com/zxrzju/SuperLine3D)]
- [What Matters for 3D Scene Flow Network](https://arxiv.org/pdf/2207.09143.pdf) [`scene flow`; [PyTorch](https://github.com/IRMVLab/3DFlow)]
- [Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation](https://arxiv.org/pdf/2207.09084.pdf) [`seg`]
- [Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes](https://arxiv.org/pdf/2207.08656.pdf) [`reconstruction`; [Github](https://github.com/UncleMEDM/InstPIFu)]
- [JPerceiver: Joint Perception Network for Depth, Pose and Layout Estimation in Driving Scenes](https://arxiv.org/pdf/2207.07895.pdf) [`autonomous driving`; [PyTorch](https://github.com/sunnyHelen/JPerceiver)]
- [TransGrasp: Grasp Pose Estimation of a Category of Objects by Transferring Grasps from Only One Labeled Instance](https://arxiv.org/pdf/2207.07861.pdf) [`pose estimation`; [PyTorch](https://github.com/yanjh97/TransGrasp)]
- [CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinement](https://arxiv.org/pdf/2207.08082.pdf) [`pose estimation`; [PyTorch](https://github.com/THU-DA-6D-Pose-Group/CATRE)]
- [Lidar Point Cloud Guided Monocular 3D Object Detection](https://arxiv.org/pdf/2104.09035.pdf) [`det`, `monocular`; [PyTorch](https://github.com/SPengLiang/LPCG)]
- [DID-M3D: Decoupling Instance Depth for Monocular 3D Object Detection](https://arxiv.org/pdf/2207.08531.pdf) [`det`, `monocular`; [PyTorch](https://github.com/SPengLiang/DID-M3D)]
- [ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning](https://arxiv.org/pdf/2207.07601.pdf) [`autonomous driving`; [PyTorch](https://github.com/OpenPerceptionX/ST-P3)]
- [3D Instances as 1D Kernels](https://arxiv.org/pdf/2207.07372.pdf) [`seg`; [PyTorch](https://github.com/W1zheng/DKNet)]
- [Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation](https://arxiv.org/pdf/2207.07522.pdf) [`scene flow`; [PyTorch](https://github.com/cwc1260/BiFlow)]
- [Rethinking IoU-based Optimization for Single-stage 3D Object Detection](https://arxiv.org/pdf/2207.09332.pdf) [`det`; [Github](https://github.com/hlsheng1/RDIoU)]
- [Meta-Sampler: Almost-Universal yet Task-Oriented Sampling for Point Clouds](https://arxiv.org/pdf/2203.16001.pdf) [`sampling`]
- [CPO: Change Robust Panorama to Point Cloud Localization](https://arxiv.org/pdf/2207.05317.pdf) [`visual localization`]
- [Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networks](https://arxiv.org/pdf/2207.05444.pdf) [`pose estimation`; [PyTorch](https://github.com/JiehongLin/Self-DPDN)]
- [Hierarchical Latent Structure for Multi-Modal Vehicle Trajectory Forecasting](https://arxiv.org/pdf/2207.04624.pdf) [`autonomous driving`; [PyTorch](https://github.com/d1024choi/HLSTrajForecast)]
- [2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds](https://arxiv.org/pdf/2207.04397.pdf) [`seg`; [Github](https://github.com/yanx27/2DPASS)]
- [A Closer Look at Invariances in Self-supervised Pre-training for 3D Vision](https://arxiv.org/pdf/2207.04997.pdf) [`self-supervised`]
- [Open-world Semantic Segmentation for LIDAR Point Clouds](https://arxiv.org/pdf/2207.01452.pdf) [`seg`; [PyTorch](https://github.com/Jun-CEN/Open_world_3D_semantic_segmentation)]
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://arxiv.org/pdf/2203.17270.pdf) [`det`, `seg`; [Github](https://github.com/zhiqi-li/BEVFormer)]
- [LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection](https://arxiv.org/pdf/2203.14956.pdf) [`det`; [PyTorch](https://github.com/weiyithu/LiDAR-Distillation)]
- [FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection](https://arxiv.org/pdf/2112.00322v1.pdf) [`det`; [PyTorch](https://github.com/samsunglabs/fcaf3d)]
- [Masked Autoencoders for Point Cloud Self-supervised Learning](https://arxiv.org/pdf/2203.06604.pdf) [`self-supervised`; [PyTorch](https://github.com/Pang-Yatian/Point-MAE)]
- [PETR: Position Embedding Transformation for Multi-View 3D Object Detection](https://arxiv.org/pdf/2203.05625.pdf) [`det`; [PyTorch](https://github.com/megvii-research/PETR)]
- [Learning Ego 3D Representation as Ray Tracing](https://arxiv.org/pdf/2206.04042.pdf) [`autonomous driving`; [PyTorch](https://github.com/fudan-zvg/Ego3RT)]
- [AutoAlignV2: Deformable Feature Aggregation for Dynamic Multi-Modal 3D Object Detection](https://arxiv.org/pdf/2207.10316.pdf) [`det`; [Github](https://github.com/zehuichen123/AutoAlignV2)]
- CVPR
- [Bridged Transformer for Vision and Point Cloud 3D Object Detection](https://arxiv.org/pdf/2210.01391.pdf) [`det`]
- [ShapeFormer: Transformer-based Shape Completion via Sparse Representation](https://arxiv.org/pdf/2201.10326.pdf) [`completion`; [PyTorch](https://github.com/qheldiv/shapeformer)]
- [RBGNet: Ray-based Grouping for 3D Object Detection](https://arxiv.org/pdf/2204.02251.pdf) [`det`; [Github](https://github.com/Haiyang-W/RBGNet)]
- [Boosting 3D Object Detection by Simulating Multimodality on Point Clouds](https://arxiv.org/pdf/2206.14971.pdf) [`det`]
- [MonoGround: Detecting Monocular 3D Objects from the Ground](https://arxiv.org/pdf/2206.07372.pdf) [`det`, `monocular`; [Github](https://github.com/cfzd/MonoGround)]
- [PlanarRecon: Real-time 3D Plane Detection and Reconstruction from Posed Monocular Videos](https://arxiv.org/pdf/2206.07710.pdf) [`reconstruction`; [PyTorch](https://github.com/neu-vi/planarrecon)]
- [Learning 3D Object Shape and Layout without 3D Supervision](https://arxiv.org/pdf/2206.07028.pdf) [`shape`, `layout`; [Project](https://gkioxari.github.io/usl/)]
- [Deterministic Point Cloud Registration via Novel Transformation Decomposition](https://openaccess.thecvf.com/content/CVPR2022/papers/Chen_Deterministic_Point_Cloud_Registration_via_Novel_Transformation_Decomposition_CVPR_2022_paper.pdf) [`registration`]
- [Cross-view Transformers for real-time Map-view Semantic Segmentation](https://arxiv.org/pdf/2205.02833.pdf) [`autonomous driving`; [PyTorch](https://github.com/bradyz/cross_view_transformers)]
- [RIDDLE: Lidar Data Compression with Range Image Deep Delta Encoding](https://arxiv.org/pdf/2206.01738.pdf) [`compression`]
- [CodedVTR: Codebook-based Sparse Voxel Transformer with Geometric Guidance](https://arxiv.org/pdf/2203.09887v1.pdf) [`seg`; [PyTorch](https://github.com/A-suozhang/CodedVTR)]
- [Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation](https://arxiv.org/pdf/2206.02099.pdf) [`seg`; [Github](https://github.com/cardwing/Codes-for-PVKD)]
- [Voxel Field Fusion for 3D Object Detection](https://arxiv.org/pdf/2205.15938.pdf) [`det`; [PyTorch](https://github.com/dvlab-research/VFF)]
- [On the Choice of Data for Efficient Training and Validation of End-to-End Driving Models](https://arxiv.org/pdf/2206.00608.pdf) [`autonomous driving`; CVPRW]
- [3PSDF: Three-Pole Signed Distance Function for Learning Surfaces with Arbitrary Topologies](https://arxiv.org/pdf/2205.15572.pdf) [`reconstruction`]
- [The Devil is in the Pose: Ambiguity-free 3D Rotation-invariant Learning via Pose-aware Convolution](https://arxiv.org/pdf/2205.15210.pdf) [`cls`, `seg`]
- [Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priors](https://arxiv.org/pdf/2205.14886.pdf) [`shape mating`; [Project](https://neural-shape-mating.github.io)]
- [Time3D: End-to-End Joint Monocular 3D Object Detection and Tracking for Autonomous Driving](https://arxiv.org/pdf/2205.14882.pdf) [`autonomous driving`, `monocular`]
- [SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation](https://arxiv.org/pdf/2205.13490.pdf) [`seg`; [PyTorch](https://github.com/wangzy22/SemAffiNet)]
- [Primitive3D: 3D Object Dataset Synthesis from Randomly Assembled Primitives](https://arxiv.org/pdf/2205.12627.pdf) [`cls`]
- [RCP: Recurrent Closest Point for Scene Flow Estimation on 3D Point Clouds](https://arxiv.org/pdf/2205.11028.pdf) [`scene flow`; [Github](https://github.com/gxd1994/RCP)]
- [Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detection](https://arxiv.org/pdf/2205.09373.pdf) [`det`]
- [Surface Representation for Point Clouds](https://arxiv.org/pdf/2205.05740.pdf) [`cls`, `seg`, `det`; [PyTorch](https://github.com/hancyran/RepSurf)]
- [FvOR: Robust Joint Shape and Pose Optimization for Few-view Object Reconstruction](https://arxiv.org/pdf/2205.07763.pdf) [`reconstruction`; [PyTorch](https://github.com/zhenpeiyang/FvOR/)]
- [Topologically-Aware Deformation Fields for Single-View 3D Reconstruction](https://arxiv.org/pdf/2205.06267.pdf) [`reconstruction`; [Project](https://shivamduggal4.github.io/tars-3D/)]
- [Deep Orientation-Aware Functional Maps: Tackling Symmetry Issues in Shape Matching](https://arxiv.org/pdf/2204.13453.pdf) [`matching`; [PyTorch](https://github.com/nicolasdonati/DUO-FM)]
- [Rotationally Equivariant 3D Object Detection](https://arxiv.org/pdf/2204.13630.pdf) [`det`; [Project](https://kovenyu.com/eon/)]
- [MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation](https://arxiv.org/pdf/2204.12667.pdf) [`seg`; [Project](https://www.nec-labs.com/~mas/MM-TTA/)]
- [Density-preserving Deep Point Cloud Compression](https://arxiv.org/pdf/2204.12684.pdf) [`compression`; [PyTorch](https://github.com/yunhe20/D-PCC)]
- [Coupled Iterative Refinement for 6D Multi-Object Pose Estimation](https://arxiv.org/pdf/2204.12516.pdf) [`pose estimation`; [PyTorch](https://github.com/princeton-vl/Coupled-Iterative-Refinement)]
- [A Scalable Combinatorial Solver for Elastic Geometrically Consistent 3D Shape Matching](https://arxiv.org/pdf/2204.12805.pdf) [`match`; [Github](https://github.com/paul0noah/sm-comb)]
- [Focal Sparse Convolutional Networks for 3D Object Detection](https://arxiv.org/pdf/2204.12463.pdf) [`det`; [PyTorch](https://github.com/dvlab-research/FocalsConv)]
- [Surface Reconstruction from Point Clouds by Learning Predictive Context Priors](https://arxiv.org/pdf/2204.11015.pdf) [`reconstruction`; [Tensorflow](https://github.com/mabaorui/PredictableContextPrior)]
- [Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priors](https://arxiv.org/pdf/2204.10603.pdf) [`reconstruction`; [Tensorflow](https://github.com/mabaorui/OnSurfacePrior)]
- [Forecasting from LiDAR via Future Object Detection](https://arxiv.org/pdf/2203.16297.pdf) [`forecasting`; [PyTorch](https://github.com/neeharperi/FutureDet)]
- [Fast Point Transformer](https://arxiv.org/pdf/2112.04702.pdf) [`seg`, `det`; [PyTorch](https://github.com/POSTECH-CVLab/FastPointTransformer)]
- [Proposal-free Lidar Panoptic Segmentation with Pillar-level Affinity](https://arxiv.org/pdf/2204.08744.pdf) [`seg`; CVPRW]
- [Multi-Camera Multiple 3D Object Tracking on the Move for Autonomous Vehicles](https://arxiv.org/pdf/2204.09151.pdf) [`autonomous driving`; CVPRW]
- [Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation](https://arxiv.org/pdf/2204.07548.pdf) [`seg`; [PyTorch](https://github.com/drprojects/DeepViewAgg)]
- [OccAM's Laser: Occlusion-based Attribution Maps for 3D Object Detectors on LiDAR Data](https://arxiv.org/pdf/2204.06577.pdf) [`det`; [PyTorch](https://github.com/dschinagl/occam)]
- [3DeformRS: Certifying Spatial Deformations on Point Clouds](https://arxiv.org/pdf/2204.05687.pdf) [`robustness`; [Github](https://github.com/gaperezsa/3DeformRS)]
- [HyperDet3D: Learning a Scene-conditioned 3D Object Detector](https://arxiv.org/pdf/2204.05599.pdf) [`det`]
- [Exploiting Temporal Relations on Radar Perception for Autonomous Driving](https://arxiv.org/pdf/2204.01184.pdf) [`autonomous driving`]
- [Homography Loss for Monocular 3D Object Detection](https://arxiv.org/pdf/2204.00754.pdf) [`det`]
- [CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detection](https://arxiv.org/pdf/2204.00325.pdf) [`det`]
- [Learning to Detect Mobile Objects from LiDAR Scans Without Labels](https://arxiv.org/pdf/2203.15882.pdf) [`det`; [PyTorch](https://github.com/YurongYou/MODEST)]
- [Learning Local Displacements for Point Cloud Completion](https://arxiv.org/pdf/2203.16600.pdf) [`completion`]
- [Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds](https://arxiv.org/pdf/2203.16895.pdf) [`scene flow`; [Github](https://github.com/leolyj/DCA-SRSFE)]
- [LiDAR Snowfall Simulation for Robust 3D Object Detection](https://arxiv.org/pdf/2203.15118.pdf) [`det`; [Github](https://github.com/SysCV/LiDAR_snow_sim)]
- [Text2Pos: Text-to-Point-Cloud Cross-Modal Localization](https://arxiv.org/pdf/2203.15125.pdf) [`localization`; [PyTorch](https://github.com/mako443/Text2Pos-CVPR2022)]
- [Stratified Transformer for 3D Point Cloud Segmentation](https://arxiv.org/pdf/2203.14508.pdf) [`seg`; [PyTorch](https://github.com/dvlab-research/Stratified-Transformer)]
- [REGTR: End-to-end Point Cloud Correspondences with Transformers](https://arxiv.org/pdf/2203.14517.pdf) [`registration`; [PyTorch](https://github.com/yewzijian/RegTR)]
- [Equivariant Point Cloud Analysis via Learning Orientations for Message Passing](https://arxiv.org/pdf/2203.14486.pdf) [`cls`, `seg`, `normal estimation`; [Github](https://github.com/luost26/Equivariant-OrientedMP)]
- [SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration](https://arxiv.org/pdf/2203.14453.pdf) [`registration`; [Github](https://github.com/ZhiChen902/SC2-PCR)]
- [Multi-instance Point Cloud Registration by Efficient Correspondence Clustering](https://arxiv.org/pdf/2111.14582.pdf) [`registration`]
- [Towards Implicit Text-Guided 3D Shape Generation](https://arxiv.org/pdf/2203.14622.pdf) [`generation`; [PyTorch](https://github.com/liuzhengzhe/Towards-Implicit-Text-Guided-Shape-Generation)]
- [Point2Seq: Detecting 3D Objects as Sequences](https://arxiv.org/pdf/2203.13394v1.pdf) [`det`; [PyTorch](https://github.com/ocNflag/point2seq)]
- [MonoDETR: Depth-aware Transformer for Monocular 3D Object Detection](https://arxiv.org/pdf/2203.13310v1.pdf) [`det`, `monocular`; [Github](https://github.com/ZrrSkywalker/MonoDETR)]
- [AziNorm: Exploiting the Radial Symmetry of Point Cloud for Azimuth-Normalized 3D Perception](https://arxiv.org/pdf/2203.13090v1.pdf) [`det`, `seg`; [Github](https://github.com/hustvl/AziNorm)]
- [IDEA-Net: Dynamic 3D Point Cloud Interpolation via Deep Embedding Alignment](https://arxiv.org/pdf/2203.11590v1.pdf) [`interpolation`; [Github](https://github.com/ZENGYIMING-EAMON/IDEA-Net)]
- [TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers](https://arxiv.org/pdf/2203.11496v1.pdf) [`det`; [PyTorch](https://github.com/XuyangBai/TransFusion/)]
- [Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds](https://arxiv.org/pdf/2203.11139v1.pdf) [`det`; [PyTorch](https://github.com/yifanzhang713/IA-SSD)]
- [No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfaces](https://arxiv.org/pdf/2203.11113v1.pdf) [`cls`; [Github](https://github.com/jx-zhong-for-academic-purpose/Kinet)]
- [MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer](https://arxiv.org/pdf/2203.10981v1.pdf) [`det`, `monocular`; [Github](https://github.com/kuanchihhuang/MonoDTR)]
- [Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds](https://arxiv.org/pdf/2203.10314v1.pdf) [`det`; [PyTorch](https://github.com/skyhehe123/VoxSeT)]
- [VISTA: Boosting 3D Object Detection via Dual Cross-VIew SpaTial Attention](https://arxiv.org/pdf/2203.09704v1.pdf) [`det`; [PyTorch](https://github.com/Gorilla-Lab-SCUT/VISTA)]
- [Sparse Fuse Dense: Towards High Quality 3D Detection with Depth Completion](https://arxiv.org/pdf/2203.09780v1.pdf) [`det`]
- [AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation](https://arxiv.org/pdf/2203.09516v1.pdf) [`completion`, `reconstruction`, `generation`]
- [DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection](https://arxiv.org/pdf/2203.08195v1.pdf) [`det`; [Tensorflow](https://github.com/tensorflow/lingvo/tree/master/lingvo)]
- [Scribble-Supervised LiDAR Semantic Segmentation](https://arxiv.org/pdf/2203.08537v1.pdf) [`seg`; [Github](https://github.com/ouenal/scribblekitti)]
- [MonoJSG: Joint Semantic and Geometric Cost Volume for Monocular 3D Object Detection](https://arxiv.org/pdf/2203.08563v1.pdf) [`det`, `monocular`; [Github](https://github.com/lianqing11/MonoJSG)]
- [PTTR: Relational 3D Point Cloud Object Tracking with Transformer](https://arxiv.org/pdf/2112.02857.pdf) [`tracking`; [PyTorch](https://github.com/Jasonkks/PTTR)]
- [AutoGPart: Intermediate Supervision Search for Generalizable 3D Part Segmentation](https://arxiv.org/pdf/2203.06558.pdf) [`seg`]
- [Point Density-Aware Voxels for LiDAR 3D Object Detection](https://arxiv.org/pdf/2203.05662.pdf) [`det`; [Github](https://github.com/TRAILab/PDV)]
- [Contrastive Boundary Learning for Point Cloud Segmentation](https://arxiv.org/pdf/2203.05272.pdf) [`seg`; [Github](https://github.com/LiyaoTang/contrastBoundary)]
- [Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement](https://arxiv.org/pdf/2203.05238.pdf) [`det`; [PyTorch](https://github.com/xuxw98/BackToReality)]
- [Shape-invariant 3D Adversarial Point Clouds](https://arxiv.org/pdf/2203.04041.pdf) [`adversarial`; [Github](https://github.com/shikiw/SI-Adv)]
- [Iterative Corresponding Geometry: Fusing Region and Depth for Highly Efficient 3D Tracking of Textureless Objects](https://arxiv.org/pdf/2203.05334.pdf) [`tracking`; [Github](https://github.com/DLR-RM/3DObjectTracking)]
- [ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotation](https://arxiv.org/pdf/2203.03888.pdf) [`cls`; [Github](https://github.com/robinwang1/ART-Point)]
- [Geometric Transformer for Fast and Robust Point Cloud Registration](https://arxiv.org/pdf/2202.06688.pdf) [`registration`; [PyTorch](https://github.com/qinzheng93/GeoTransformer)]
- [Lepard: Learning partial point cloud matching in rigid and deformable scenes](https://arxiv.org/pdf/2111.12591.pdf) [`registration`; [PyTorch](https://github.com/rabbityl/lepard)]
- [Pseudo-Stereo for Monocular 3D Object Detection in Autonomous Driving](https://arxiv.org/pdf/2203.02112.pdf) [`det`, `monocular`; [Github](https://github.com/revisitq/Pseudo-Stereo-3D)]
- [A Versatile Multi-View Framework for LiDAR-based 3D Object Detection with Guidance from Panoptic Segmentation](https://arxiv.org/pdf/2203.02133.pdf) [`det`]
- [Embracing Single Stride 3D Object Detector with Sparse Transformer](https://arxiv.org/pdf/2112.06375.pdf) [`det`; [PyTorch](https://github.com/TuSimple/SST)]
- [Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes](https://arxiv.org/pdf/2011.12001.pdf) [`det`; [PyTorch](https://github.com/qq456cvb/CanonicalVoting)]
- [CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding](https://arxiv.org/pdf/2203.00680.pdf) [`cross-modal learning`; [PyTorch](https://github.com/MohamedAfham/CrossPoint)]
- [PointCLIP: Point Cloud Understanding by CLIP](https://arxiv.org/pdf/2112.02413.pdf) [`cross-modal learning`; [Github](https://github.com/ZrrSkywalker/PointCLIP)]
- [SoftGroup for 3D Instance Segmentation on Point Clouds](https://arxiv.org/pdf/2203.01509v1.pdf) [`seg`; [PyTorch](https://github.com/thangvubk/SoftGroup)]
- [Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds](https://arxiv.org/pdf/2203.01730v1.pdf) [`tracking`; [PyTorch](https://github.com/Ghostish/Open3DSOT)]
- [A Unified Query-based Paradigm for Point Cloud Understanding](https://arxiv.org/pdf/2203.01252.pdf) [`det`, `seg`, `cls`]
- AAAI
- [SRCN3D: Sparse R-CNN 3D Surround-View Camera Object Detection and Tracking for Autonomous Driving](https://arxiv.org/pdf/2206.14451.pdf) [`det`, `tracking`; [PyTorch](https://github.com/synsin0/SRCN3D)]
- [Static-Dynamic Co-Teaching for Class-Incremental 3D Object Detection](https://arxiv.org/pdf/2112.07241.pdf) [`det`; [PyTorch](https://github.com/Na-Z/SDCoT)]
- [Semantic Segmentation for Point Cloud Scenes via Dilated Graph Feature Aggregation and Pyramid Decoders](https://arxiv.org/pdf/2204.04944.pdf) [`seg`]
- [SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection](https://arxiv.org/pdf/2201.01976.pdf) [`det`; [PyTorch](https://github.com/blakechen97/SASA)]
- [DuMLP-Pin: A Dual-MLP-dot-product Permutation-invariant Network for Set Feature Extraction](https://arxiv.org/pdf/2203.04007.pdf) [`cls`, `seg`; [PyTorch](https://github.com/JaronTHU/DuMLP-Pin)]
- [Reliable Inlier Evaluation for Unsupervised Point Cloud Registration](https://arxiv.org/pdf/2202.11292.pdf) [`registration`; [Github](https://github.com/supersyq/RIENet)]
- [Sparse Cross-scale Attention Network for Efficient LiDAR Panoptic Segmentation](https://arxiv.org/pdf/2201.05972.pdf) [`seg`]
- [FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registration](https://arxiv.org/pdf/2106.03479.pdf) [`registration`; [Github](https://github.com/hxwork/FINet)]
- [DetarNet: Decoupling Translation and Rotation by Siamese Network for Point Cloud Registration](https://arxiv.org/pdf/2112.14059.pdf) [`registration`; [Github](https://github.com/ZhiChen902/DetarNet)]
- [End-to-End Learning the Partial Permutation Matrix for Robust 3D Point Cloud Registration](https://arxiv.org/pdf/2110.15250.pdf) [`registration`]
- [Deep Confidence Guided Distance for 3D Partial Shape Registration](https://arxiv.org/pdf/2201.11379.pdf) [`registration`]
- [AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Clouds](https://arxiv.org/pdf/2112.09205.pdf) [`det`]
- [Joint 3D Object Detection and Tracking Using Spatio-Temporal Representation of Camera Image and LiDAR Point Clouds](https://arxiv.org/pdf/2112.07116.pdf) [`det`, `tracking`]
- [Attention-based Transformation from Latent Features to Point Clouds](https://arxiv.org/pdf/2112.05324.pdf) [`generation`]
- [Behind the Curtain: Learning Occluded Shapes for 3D Object Detection](https://arxiv.org/pdf/2112.02205.pdf) [`det`; [PyTorch](https://github.com/Xharlie/BtcDet)]
- Others
- [MoGDE: Boosting Mobile Monocular 3D Object Detection with Ground Depth Estimation](https://arxiv.org/pdf/2303.13561v1.pdf) [`det`; NeurIPS]
- [Fast-BEV: Towards Real-time On-vehicle Bird’s-Eye View Perception](https://arxiv.org/pdf/2301.07870v1.pdf) [`det`; [Github](https://github.com/Sense-GVT/Fast-BEV); NeurIPSW]
- [Sparse2Dense: Learning to Densify 3D Features for 3D Object Detection](https://arxiv.org/pdf/2211.13067.pdf) [`det`; [Github](https://github.com/stevewongv/Sparse2Dense); NeurIPS]
- [Language Conditioned Spatial Relation Reasoning for 3D Object Grounding](https://arxiv.org/pdf/2211.09646.pdf) [`localizing`; [PyTorch](https://github.com/cshizhe/vil3dref); NeurIPS]
- [A Benchmark for Out of Distribution Detection in Point Cloud 3D Semantic Segmentation](https://arxiv.org/pdf/2211.06241.pdf) [`seg`; NeurIPSW]
- [Analyzing Deep Learning Representations of Point Clouds for Real-Time In-Vehicle LiDAR Perception](https://arxiv.org/pdf/2210.14612.pdf) [`autonomous driving`; NeurIPSW]
- [HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfaces](https://arxiv.org/pdf/2210.07158.pdf) [`normal estimation`; [Github](https://github.com/LeoQLi/HSurf-Net); NeurIPS]
- [LION: Latent Point Diffusion Models for 3D Shape Generation](https://arxiv.org/pdf/2210.06978.pdf) [`generation`; [Github](https://github.com/nv-tlabs/LION); NeurIPS]
- [SageMix: Saliency-Guided Mixup for Point Clouds](https://arxiv.org/pdf/2210.06944.pdf) [`augmentation`; [Github](https://github.com/mlvlab/SageMix); NeurIPS]
- [Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection](https://arxiv.org/pdf/2210.05593.pdf) [`det`; [Github](https://github.com/CVMI-Lab/FS3D); NeurIPS]
- [Point Transformer V2: Grouped Vector Attention and Partition-based Pooling](https://arxiv.org/pdf/2210.05666.pdf) [`cls`, `seg`; [Github](https://github.com/Gofinge/PointTransformerV2); NeurIPS]
- [Let Images Give You More:Point Cloud Cross-Modal Training for Shape Analysis](https://arxiv.org/pdf/2210.04208.pdf) [`cross-modality`; [Github](https://github.com/ZhanHeshen/PointCMT); NeurIPS]
- [OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Clouds](https://arxiv.org/pdf/2210.04458.pdf) [`seg`; [PyTorch](https://github.com/vLAR-group/OGC); NeurIPS]
- [CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds](https://arxiv.org/pdf/2210.04264.pdf) [`det`; [Github](https://github.com/Haiyang-W/CAGroup3D); NeurIPS]
- [Learning Consistency-Aware Unsigned Distance Functions Progressively from Raw Point Clouds](https://arxiv.org/pdf/2210.02757.pdf) [`reconstruction`; [PyTorch](https://github.com/junshengzhou/CAP-UDF); NeurIPS]
- [PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds](https://arxiv.org/pdf/2208.00223.pdf) [`augmentation`; [PyTorch](https://github.com/xiaoaoran/polarmix); NeurIPS]
- [Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Images](https://arxiv.org/pdf/2205.13764.pdf) [`det`; NeurIPS]
- [P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting](https://arxiv.org/pdf/2208.02812.pdf) [`pre-training`; [PyTorch](https://github.com/wangzy22/P2P); NeurIPS]
- [Fully Sparse 3D Object Detection](https://arxiv.org/pdf/2207.10035.pdf) [`det`; [PyTorch](https://github.com/TuSimple/SST); NeurIPS]
- [PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies](https://arxiv.org/pdf/2206.04670.pdf) [`seg`, `cls`; [PyTorch](https://github.com/guochengqian/pointnext); NeurIPS]
- [K-Radar: 4D Radar Object Detection Dataset and Benchmark for Autonomous Driving in Various Weather Conditions](https://arxiv.org/pdf/2206.08171.pdf) [`autonomous driving`; [Github](https://github.com/kaist-avelab/K-Radar); NeurIPS Track]
- [SNAKE: Shape-aware Neural 3D Keypoint Field](https://arxiv.org/pdf/2206.01724.pdf) [`keypoints`; [PyTorch](https://github.com/zhongcl-thu/SNAKE); NeurIPS]
- [Unifying Voxel-based Representation with Transformer for 3D Object Detection](https://arxiv.org/pdf/2206.00630.pdf) [`det`; [PyTorch](https://github.com/dvlab-research/UVTR); NeurIPS]
- [Non-rigid Point Cloud Registration with Neural Deformation Pyramid](https://arxiv.org/pdf/2205.12796.pdf) [`non-rigid`, `registration`; [PyTorch](https://github.com/rabbityl/DeformationPyramid); NeurIPS]
- [One-Inlier is First: Towards Efficient Position Encoding for Point Cloud Registration](https://proceedings.neurips.cc/paper_files/paper/2022/file/2e163450c1ae3167832971e6da29f38d-Paper-Conference.pdf) [`registration`; NeurIPS]
- [DeepInteraction: 3D Object Detection via Modality Interaction](https://arxiv.org/pdf/2208.11112.pdf) [`det`; [Github](https://github.com/fudan-zvg/DeepInteraction); NeurIPS]
- [Spatial Pruned Sparse Convolution for Efficient 3D Object Detection](https://arxiv.org/pdf/2209.14201.pdf) [`det`; NeurIPS]
- [Rethinking the compositionality of point clouds through regularization in the hyperbolic space](https://arxiv.org/pdf/2209.10318.pdf) [`cls`; [Github](https://github.com/diegovalsesia/HyCoRe); NeurIPS]
- [Cross-modal Learning for Image-Guided Point Cloud Shape Completion](https://arxiv.org/pdf/2209.09552.pdf) [`completion`; [Github](https://github.com/diegovalsesia/XMFnet); NeurIPS]
- [Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Dataset](https://arxiv.org/pdf/2206.15436.pdf) [`pose estimation`; [PyTorch](https://github.com/OasisYang/Wild6D); NeurIPS]
- [GenSDF: Two-Stage Learning of Generalizable Signed Distance Functions](https://arxiv.org/pdf/2206.02780.pdf) [`representation`; [PyTorch](https://github.com/princeton-computational-imaging/gensdf); NeurIPS]
- [Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training](https://arxiv.org/pdf/2205.14401.pdf) [`self-supervised`; [PyTorch](https://github.com/ZrrSkywalker/Point-M2AE); NeurIPS]
- [BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework](https://arxiv.org/pdf/2205.13790.pdf) [`det`; [PyTorch](https://github.com/ADLab-AutoDrive/BEVFusion); NeurIPS]
- [PeRFception: Perception using Radiance Fields](https://arxiv.org/pdf/2208.11537.pdf) [`NeRF`; [PyTorch](https://github.com/POSTECH-CVLab/PeRFception); NeurIPS]
- [Stress-Testing LiDAR Registration](https://arxiv.org/pdf/2204.07719.pdf) [`registration`; [Github](https://github.com/AmnonDrory/LidarRegistration); NeurIPSW]
- [Learning Inter-Superpoint Affinity for Weakly Supervised 3D Instance Segmentation](https://arxiv.org/pdf/2210.05534.pdf) [`seg`; [PyTorch](https://github.com/fpthink/3D-WSIS); ACCV]
- [Point Cloud Upsampling via Cascaded Refinement Network](https://arxiv.org/pdf/2210.03942.pdf) [`upsampling`; [Github](https://github.com/hikvision-research/3DVision); ACCV]
- [PU-Transformer: Point Cloud Upsampling Transformer](https://arxiv.org/pdf/2111.12242.pdf) [`upsampling`; [Github](https://github.com/ShiQiu0419/PU-Transformer); ACCV]
- [Learning Object-level Point Augmentor for Semi-supervised 3D Object Detection](https://arxiv.org/pdf/2212.09273.pdf) [`det`; [PyTorch](https://github.com/nomiaro/OPA); BMVC]
- [APSNet: Attention Based Point Cloud Sampling](https://arxiv.org/pdf/2210.05638.pdf) [`sampling`; [PyTorch](https://github.com/Yangyeeee/APSNet); BMVC]
- [Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding](https://arxiv.org/pdf/2210.02798.pdf) [`unsupervised`; [PyTorch](https://github.com/gfmei/softclu); BMVC]
- [COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentation](https://arxiv.org/pdf/2210.01784.pdf) [`seg`; [PyTorch](https://github.com/cv-rits/COARSE3D); BMVC]
- [M3DETR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers](https://arxiv.org/pdf/2104.11896.pdf) [`det`
; WACV]
- [GraphReg: Dynamical Point Cloud Registration with Geometry-aware Graph Signal Processing](https://arxiv.org/pdf/2302.01109.pdf) [`registration`; [Github](https://github.com/zikai1/GraphReg); TIP]
- [R-PointHop: A Green, Accurate and Unsupervised Point Cloud Registration Method](https://arxiv.org/pdf/2103.08129.pdf) [`registration`; [Github](https://github.com/pranavkdm/R-PointHop); TIP]
- [3D Cascade RCNN: High Quality Object Detection in Point Clouds](https://arxiv.org/pdf/2211.08248.pdf) [`det`; [PyTorch](https://github.com/caiqi/Cascasde-3D); TIP]
- [Efficient 3D Point Cloud Feature Learning for Large-Scale Place Recognition](https://arxiv.org/pdf/2101.02374.pdf) [`place recognition`; [Tensorflow](https://github.com/fpthink/EPC-Net); TIP]
- [Real-time 3D Single Object Tracking with Transformer](https://arxiv.org/pdf/2209.00860.pdf) [`tracking`; [PyTorch](https://github.com/shanjiayao/PTT); TMM]
- [LighTN: Light-weight Transformer Network for Performance-overhead Tradeoff in Point Cloud Downsampling](https://arxiv.org/pdf/2202.06263.pdf) [`downsampling`; TMM]
- [Det6D: A Ground-Aware Full-Pose 3D Object Detector for Improving Terrain Robustness](https://arxiv.org/pdf/2207.09412.pdf) [`det`; [Github](https://github.com/HITSZ-NRSL/De6D); TIM]
- [Push-the-Boundary: Boundary-aware Feature Propagation for Semantic Segmentation of 3D Point Clouds](https://arxiv.org/pdf/2212.12402.pdf) [`seg`; [Github](https://github.com/shenglandu/PushBoundary); 3DV]
- [SRFeat: Learning Locally Accurate and Globally Consistent Non-Rigid Shape Correspondence](https://arxiv.org/pdf/2209.07806.pdf) [`non-rigid`, `matching`; [Github](https://github.com/craigleili/SRFeat); 3DV]
- [SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representation](https://arxiv.org/pdf/2209.05924.pdf) [`cls`, `seg`; [Github](https://github.com/zhuoinoulu/svnet); 3DV]
- [Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes](https://arxiv.org/pdf/2208.06671.pdf) [`seg`; 3DV]
- [Arbitrary Point Cloud Upsampling with Spherical Mixture of Gaussians](https://arxiv.org/pdf/2208.05274.pdf) [`upsampling`; 3DV]
- [CC-3DT: Panoramic 3D Object Tracking via Cross-Camera Fusion](https://arxiv.org/pdf/2212.01247.pdf) [`tracking`; [Project](https://www.vis.xyz/pub/cc-3dt/); CoRL]
- [Towards Long-Tailed 3D Detection](https://arxiv.org/pdf/2211.08691.pdf) [`det`; CoRL]
- [CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers](https://arxiv.org/pdf/2207.02202.pdf) [`seg`; [PyTorch](https://github.com/DerrickXuNu/CoBEVT); CoRL]
- [SSL-Lanes: Self-Supervised Learning for Motion Forecasting in Autonomous Driving](https://arxiv.org/pdf/2206.14116.pdf) [`motion forecasting`; [PyTorch](https://github.com/AutoVision-cloud/SSL-Lanes); CoRL]
- [MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation](https://arxiv.org/pdf/2203.14662.pdf) [`seg`; ICME]
- [CENet: Toward Concise and Efficient LiDAR Semantic Segmentation for Autonomous Driving](https://arxiv.org/pdf/2207.12691.pdf) [`seg`; [PyTorch](https://github.com/huixiancheng/CENet); ICME]
- [Learning to Generate 3D Shapes from a Single Example](https://arxiv.org/pdf/2208.02946.pdf) [`generation`; [PyTorch](https://github.com/ChrisWu1997/SingleShapeGen); SIGGRAPH Aisa]
- [Shape Completion with Points in the Shadow](https://arxiv.org/pdf/2209.08345.pdf) [`completion`; SIGGRAPH Aisa]
- [Neural Wavelet-domain Diffusion for 3D Shape Generation](https://arxiv.org/pdf/2209.08725.pdf) [`generation`; SIGGRAPH Aisa]
- [ImLoveNet: Misaligned Image-supported Registration Network for Low-overlap Point Cloud Pairs](https://arxiv.org/pdf/2207.00826.pdf) [`registration`; SIGGRAPH]
- [Graph-DETR3D: Rethinking Overlapping Regions for Multi-View 3D Object Detection](https://arxiv.org/pdf/2204.11582.pdf) [`det`; ACM MM]
- [GRASP-Net: Geometric Residual Analysis and Synthesis for Point Cloud Compression](https://arxiv.org/pdf/2209.04401.pdf) [`compressing`; [Github](https://github.com/InterDigitalInc/GRASP-Net); ACM MMW]
- [Paint and Distill: Boosting 3D Object Detection with Semantic Passing Network](https://arxiv.org/pdf/2207.05497.pdf) [`det`; [Github](https://github.com/jb892/SPNet); ACM MM]
- [You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors](https://arxiv.org/pdf/2109.00182.pdf) [`registration`; [PyTorch](https://github.com/HpWang-whu/YOHO); ACM MM]
- [Boosting Single-Frame 3D Object Detection by Simulating Multi-Frame Point Clouds](https://arxiv.org/pdf/2207.01030.pdf) [`det`; ACM MM]
- [LiSnowNet: Real-time Snow Removal for LiDAR Point Cloud](https://arxiv.org/pdf/2211.10023.pdf) [`autonomous driving`; IROS]
- [Patchwork++: Fast and Robust Ground Segmentation Solving Partial Under-Segmentation Using 3D Point Cloud](https://arxiv.org/pdf/2207.11919.pdf) [`seg`; [Github](https://github.com/url-kaist/patchwork-plusplus); IROS]
- [Efficient Spatial-Temporal Information Fusion for LiDAR-Based 3D Moving Object Segmentation](https://arxiv.org/pdf/2207.02201.pdf) [`seg`; [PyTorch](https://github.com/haomo-ai/MotionSeg3D); IROS]
- [3D Part Assembly Generation with Instance Encoded Transformer](https://arxiv.org/pdf/2207.01779.pdf) [`part assembly`; IROS]
- [BoxGraph: Semantic Place Recognition and Pose Estimation from 3D LiDAR](https://arxiv.org/pdf/2206.15154.pdf) [`place recognition`; IROS]
- [Benchmarking and Analyzing Point Cloud Classification under Corruptions](https://arxiv.org/pdf/2202.03377.pdf) [`cls`; [PyTorch](https://github.com/jiawei-ren/ModelNet-C); ICML]
- [AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detection](https://arxiv.org/pdf/2201.06493.pdf) [`det`; IJCAI]
- [BiCo-Net: Regress Globally, Match Locally for Robust 6D Pose Estimation](https://arxiv.org/pdf/2205.03536.pdf) [`pose estimation`; IJCAI]
- [Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds](https://arxiv.org/pdf/2204.10688.pdf) [`captioning`; [Github](https://github.com/heng-hw/SpaCap3D); IJCAI]
- [Robust Point Cloud Segmentation with Noisy Annotations](https://arxiv.org/pdf/2212.03242.pdf) [`seg`; [PyTorch](https://github.com/pleaseconnectwifi/PNAL); TPAMI]
- [Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image](https://arxiv.org/pdf/2208.13241.pdf) [`reconstruction`; [PyTorch](https://github.com/aim-uofa/AdelaiDepth); TPAMI]
- [Robust Point Cloud Registration Framework Based on Deep Graph Matching](https://arxiv.org/pdf/2211.04696.pdf) [`registration`; [PyTorch](https://github.com/fukexue/RGM); TPAMI]
- [TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving](https://arxiv.org/pdf/2205.15997.pdf) [`autonomous driving`; [PyTorch](https://github.com/autonomousvision/transfuser); TPAMI]
- [Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization](https://arxiv.org/pdf/2209.10839.pdf) [`det`; TPAMI]
- [Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Clouds](https://arxiv.org/pdf/2207.12659.pdf) [`det`; TPAMI]
- [Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes](https://arxiv.org/pdf/2208.08621.pdf) [`det`; TPAMI]
- [PVNAS: 3D Neural Architecture Search with Point-Voxel Convolution](https://arxiv.org/pdf/2204.11797.pdf) [`seg`, `det`; TPAMI]
- [Pixel2Mesh++: 3D Mesh Generation and Refinement from Multi-View Images](https://arxiv.org/pdf/2204.09866.pdf) [`generation`, `mesh`; TPAMI]
- [Refine-Net: Normal Refinement Neural Network for Noisy Point Clouds](https://arxiv.org/pdf/2203.12514v1.pdf) [`normal refinement`; [PyTorch](https://github.com/hrzhou2/refinenet); TPAMI]
- [PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Paths](https://arxiv.org/pdf/2202.09507.pdf) [`completion`; [PyTorch](https://github.com/diviswen/PMP-Net); TPAMI]
- [A New Outlier Removal Strategy Based on Reliability of Correspondence Graph for Fast Point Cloud Registration](https://arxiv.org/pdf/2205.07404.pdf) [`registration`; [Github](https://github.com/WPC-WHU/GROR); TPAMI]
- [DSGN++: Exploiting Visual-Spatial Relation for Stereo-based 3D Detectors](https://arxiv.org/pdf/2204.03039.pdf) [`det`; [PyTorch](https://github.com/chenyilun95/DSGN2); TPAMI]
- [Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer](https://arxiv.org/pdf/2202.09367.pdf) [`completion`; [PyTorch](https://github.com/AllenXiangX/SnowflakeNet); TPAMI]
- [Sparse Tensor-based Multiscale Representation for Point Cloud Geometry Compression](https://arxiv.org/pdf/2111.10633.pdf) [`compression`; [Github](https://github.com/NJUVISION/SparsePCGC); TPAMI]
- [Multiway Non-rigid Point Cloud Registration via Learned Functional Map Synchronization](https://arxiv.org/pdf/2111.12878.pdf) [`registration`, `non-rigid`; [Github](https://github.com/huangjh-pub/synorim)]
- [WSDesc: Weakly Supervised 3D Local Descriptor Learning for Point Cloud Registration](https://arxiv.org/pdf/2108.02740.pdf) [`registration`; [PyTorch](https://github.com/craigleili/WSDesc); TVCG]
- [Point Set Self-Embedding](https://arxiv.org/pdf/2202.13577.pdf) [`embedding`; [Github](https://github.com/liruihui/Self-Embedding); TVCG]
- [3DMNDT: 3D multi-view registration method based on the normal distributions transform](https://arxiv.org/pdf/2103.11084.pdf) [`registration`; TASE]
- [PV-RCNN++: Semantical Point-Voxel Feature Interaction for 3D Object Detection](https://arxiv.org/pdf/2208.13414.pdf) [`det`; TVC]
- [SHRED: 3D Shape Region Decomposition with Learned Local Operations](https://arxiv.org/pdf/2206.03480.pdf) [`decomposition`; TOG]
- [SoftPool++: An Encoder-Decoder Network for Point Cloud Completion](https://arxiv.org/pdf/2205.03899.pdf) [`completion`; IJCV]
- [RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learning](https://arxiv.org/pdf/2202.13094.pdf) [`cls`, `seg`, `retrieval`; IJCV]
- [Enhanced Prototypical Learning for Unsupervised Domain Adaptation in LiDAR Semantic Segmentation](https://arxiv.org/pdf/2205.11419.pdf) [`seg`; ICRA]
- [SMAC-Seg: LiDAR Panoptic Segmentation via Sparse Multi-directional Attention Clustering](https://arxiv.org/pdf/2108.13588.pdf) [`seg`]
- [CPGNet: Cascade Point-Grid Fusion Network for Real-Time LiDAR Semantic Segmentation](https://arxiv.org/pdf/2204.09914.pdf) [`seg`; ICRA]
- [Multi-Class 3D Object Detection with Single-Class Supervision](https://arxiv.org/pdf/2205.05703.pdf) [`det`; ICRA]
- [Learning 6-DoF Object Poses to Grasp Category-level Objects by Language Instructions](https://arxiv.org/pdf/2205.04028.pdf) [`pose estimation`; [Project](https://baboon527.github.io/lang_6d/); ICRA]
- [HiTPR: Hierarchical Transformer for Place Recognition in Point Cloud](https://arxiv.org/pdf/2204.05481.pdf) [`place recognition`; ICRA]
- [RMS-FlowNet: Efficient and Robust Multi-Scale Scene Flow Estimation for Large-Scale Point Clouds](https://arxiv.org/pdf/2204.00354.pdf) [`scene flow`; ICRA]
- [Variable Rate Compression for Raw 3D Point Clouds](https://arxiv.org/pdf/2202.13862.pdf) [`compression`; [Github](https://github.com/robotic-vision-lab/Variable-Rate-Compression-For-Raw-3D-Point-Clouds); ICRA]
- [Hindsight is 2020: Leveraging Past Traversals to Aid 3D Perception](https://arxiv.org/pdf/2203.11405v1.pdf) [`det`; [PyTorch](https://github.com/YurongYou/Hindsight); ICLR]
- [WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection](https://arxiv.org/pdf/2203.08332v1.pdf) [`det`, `monocular`; [Github](https://github.com/SPengLiang/WeakM3D); ICLR]
- [Partial Wasserstein Adversarial Network for Non-rigid Point Set Registration](https://arxiv.org/pdf/2203.02227.pdf) [`non-rigid`, `registration`; ICLR]
- [A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion](https://arxiv.org/pdf/2112.03530.pdf) [`completion`; [PyTorch](https://github.com/ZhaoyangLyu/Point_Diffusion_Refinement); ICLR]
- [Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework](https://arxiv.org/pdf/2202.07123.pdf) [`cls`, `seg`; [PyTorch](https://github.com/ma-xu/pointMLP-pytorch); ICLR]
- [MonoDistill: Learning Spatial Features for Monocular 3D Object Detection](https://arxiv.org/pdf/2201.10830v1.pdf) [`det`, `monocular`; [Github](https://github.com/monster-ghost/MonoDistill); ICLR]
- [Robust 3D Object Detection in Cold Weather Conditions](https://arxiv.org/pdf/2205.11925.pdf) [`det`; IV]
- [urban_road_filter: A real-time LIDAR-based urban road and sidewalk detection algorithm for autonomous vehicles](https://www.mdpi.com/1424-8220/22/1/194/pdf) [`det`, `autonomous driving`; [Github](https://github.com/jkk-research/urban_road_filter); [Video](https://www.youtube.com/watch?v=T2qi4pldR-E); Sensors]
- [GraffMatch: Global Matching of 3D Lines and Planes for Wide Baseline LiDAR Registration](https://arxiv.org/pdf/2212.12745.pdf) [`registration`; RAL]
- [IMFNet: Interpretable Multimodal Fusion for Point Cloud Registration](https://arxiv.org/pdf/2111.09624.pdf) [`registration`; [PyTorch](https://github.com/XiaoshuiHuang/IMFNet); RAL]
- [Exploiting More Information in Sparse Point Cloud for 3D Single Object Tracking](https://arxiv.org/pdf/2210.00519.pdf) [`tracking`; [Github](https://github.com/3bobo/smat); RAL]
- [DeepFusionMOT: A 3D Multi-Object Tracking Framework Based on Camera-LiDAR Fusion with Deep Association](https://arxiv.org/pdf/2202.12100.pdf) [`tracking`; [Github](https://github.com/wangxiyang2022/DeepFusionMOT); RAL]
- [BIMS-PU: Bi-Directional and Multi-Scale Point Cloud Upsampling](https://arxiv.org/pdf/2206.12648.pdf) [`upsampling`; RAL]
- [Receding Moving Object Segmentation in 3D LiDAR Data Using Sparse 4D Convolutions](https://arxiv.org/pdf/2206.04129.pdf) [`seg`; [Github](https://github.com/PRBonn/4DMOS); RAL]
- [Temporal Point Cloud Completion with Pose Disturbance](https://arxiv.org/pdf/2202.03084.pdf) [`completion`; RAL]
- [PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds](https://arxiv.org/pdf/2109.05566.pdf) [`det`; [PyTorch](https://github.com/OPEN-AIR-SUN/PQ-Transformer); RAL]
- [Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance Segmentation](https://arxiv.org/pdf/2208.04766.pdf) [`seg`; [Tensorflow](https://github.com/isunchy/3d_instance_segmentation); CVM]
- [Semi-supervised 3D shape segmentation with multilevel consistency and part substitution](https://arxiv.org/pdf/2204.08824.pdf) [`seg`; [Tensorflow](https://github.com/isunchy/semi_supervised_3d_segmentation); CVM]
- [Point cloud completion on structured feature map with feedback network](https://arxiv.org/pdf/2202.08583.pdf) [`completion`; CVM]
- [TorchSparse: Efficient Point Cloud Inference Engine](https://arxiv.org/pdf/2204.10319.pdf) [`engine`; [PyTorch](https://github.com/mit-han-lab/torchsparse); MLSys]
- [SIENet: Spatial Information Enhancement Network for 3D Object Detection from Point Cloud](https://arxiv.org/pdf/2103.15396.pdf) [`det`; [Github](https://github.com/Liz66666/SIENet); PR]
- arXiv
- [TiG-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning](https://arxiv.org/pdf/2212.13979.pdf) [`det`; [Github](https://github.com/ADLab3Ds/TiG-BEV)]
- [ADAS: A Simple Active-and-Adaptive Baseline for Cross-Domain 3D Semantic Segmentation](https://arxiv.org/pdf/2212.10390.pdf) [`seg`; [PyTorch](https://github.com/Fayeben/ADAS)]
- [3D Point Cloud Pre-training with Knowledge Distillation from 2D Images](https://arxiv.org/pdf/2212.08974.pdf) [`pre-training`]
- [Point-E: A System for Generating 3D Point Clouds from Complex Prompts](https://arxiv.org/pdf/2212.08751.pdf) [`generation`; [PyTorch](https://github.com/openai/point-e)]
- [DETR4D: Direct Multi-View 3D Object Detection with Sparse Attention](https://arxiv.org/pdf/2212.07849.pdf) [`det`]
- [BEV-MAE: Bird's Eye View Masked Autoencoders for Outdoor Point Cloud Pre-training](https://arxiv.org/pdf/2212.05758.pdf) [`pre-training`]
- [Synthetic-to-Real Domain Generalized Semantic Segmentation for 3D Indoor Point Clouds](https://arxiv.org/pdf/2212.04668.pdf) [`seg`]
- [SemanticBEVFusion: Rethink LiDAR-Camera Fusion in Unified Bird's-Eye View Representation for 3D Object Detection](https://arxiv.org/pdf/2212.04675.pdf) [`det`]
- [3D Point Positional Encoding for Multi-Camera 3D Object Detection Transformers](https://arxiv.org/pdf/2211.14710.pdf) [`det`]
- [PVT3D: Point Voxel Transformers for Place Recognition from Sparse Lidar Scans](https://arxiv.org/pdf/2211.12542.pdf) [`place recognition`]
- [ONeRF: Unsupervised 3D Object Segmentation from Multiple Views](https://arxiv.org/pdf/2211.12038.pdf) [`seg`, `reconstruction`]
- [Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusion](https://arxiv.org/pdf/2211.10581.pdf) [`det`]
- [Adaptive Edge-to-Edge Interaction Learning for Point Cloud Analysis](https://arxiv.org/pdf/2211.10888.pdf) [`cls`, `seg`]
- [3D-QueryIS: A Query-based Framework for 3D Instance Segmentation](https://arxiv.org/pdf/2211.09375.pdf) [`seg`]
- [Towards 3D Object Detection with 2D Supervision](https://arxiv.org/pdf/2211.08287.pdf) [`det`]
- [Structured Knowledge Distillation Towards Efficient and Compact Multi-View 3D Detection](https://arxiv.org/pdf/2211.08398.pdf) [`det`]
- [Point-DAE: Denoising Autoencoders for Self-supervised Point Cloud Learning](https://arxiv.org/pdf/2211.06841.pdf) [`self-supervised`; [Github](https://github.com/YBZh/Point-DAE)]
- [3D Reconstruction of Multiple Objects by mmWave Radar on UAV](https://arxiv.org/pdf/2211.02150.pdf) [`reconstruction`]
- [Ground Plane Matters: Picking Up Ground Plane Prior in Monocular 3D Object Detection](https://arxiv.org/pdf/2211.01556.pdf) [`det`]
- [Point-Voxel Adaptive Feature Abstraction for Robust Point Cloud Classification](https://arxiv.org/pdf/2210.15514.pdf) [`cls`; [PyTorch](https://github.com/zhulf0804/PV-Ada)]
- [LidarAugment: Searching for Scalable 3D LiDAR Data Augmentations](https://arxiv.org/pdf/2210.13488.pdf) [`augmentation`]
- [Domain Adaptation in 3D Object Detection with Gradual Batch Alternation Training](https://arxiv.org/pdf/2210.10180.pdf) [`det`]
- [Zero-shot Point Cloud Segmentation by Transferring Geometric Primitives](https://arxiv.org/pdf/2210.09923.pdf) [`seg`]
- [Common Corruption Robustness of Point Cloud Detectors: Benchmark and Enhancement](https://arxiv.org/pdf/2210.05896.pdf) [`det`]
- [FusionRCNN: LiDAR-Camera Fusion for Two-stage 3D Object Detection](https://arxiv.org/pdf/2209.10733.pdf) [`det`; [Github](https://github.com/xxlbigbrother/Fusion-RCNN)]
- [LidarMultiNet: Towards a Unified Multi-task Network for LiDAR Perception](https://arxiv.org/pdf/2209.09385.pdf) [`det`]
- [4DenoiseNet: Adverse Weather Denoising from Adjacent Point Clouds](https://arxiv.org/pdf/2209.07121.pdf) [`autonomous driving`]
- [CRAFT: Camera-Radar 3D Object Detection with Spatio-Contextual Fusion Transformer](https://arxiv.org/pdf/2209.06535.pdf) [`det`]
- [M^2-3DLaneNet: Multi-Modal 3D Lane Detection](https://arxiv.org/pdf/2209.05996.pdf) [`det`]
- [ISS: Image as Stetting Stone for Text-Guided 3D Shape Generation](https://arxiv.org/pdf/2209.04145.pdf) [`generation`]
- [CAMO-MOT: Combined Appearance-Motion Optimization for 3D Multi-Object Tracking with Camera-LiDAR Fusion](https://arxiv.org/pdf/2209.02540.pdf) [`tracking`]
- [Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions](https://arxiv.org/pdf/2201.12296.pdf) [`robustness`; [PyTorch](https://github.com/jiachens/ModelNet40-C)]
- [Scatter Points in Space: 3D Detection from Multi-view Monocular Images](https://arxiv.org/pdf/2208.14738.pdf) [`det`]
- [Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction](https://arxiv.org/pdf/2208.12697.pdf) [`reconstruction`]
- [Bridging the View Disparity of Radar and Camera Features for Multi-modal Fusion 3D Object Detection](https://arxiv.org/pdf/2208.12079.pdf) [`det`]
- [AGO-Net: Association-Guided 3D Point Cloud Object Detection Network](https://arxiv.org/pdf/2208.11658.pdf) [`det`]
- [Quality Matters: Embracing Quality Clues for Robust 3D Multi-Object Tracking](https://arxiv.org/pdf/2208.10976.pdf) [`tracking`]
- [STS: Surround-view Temporal Stereo for Multi-view 3D Detection](https://arxiv.org/pdf/2208.10145.pdf) [`det`]
- [PointDP: Diffusion-driven Purification against Adversarial Attacks on 3D Point Cloud Recognition](https://arxiv.org/pdf/2208.09801.pdf) [`adversarial attack`]
- [PersDet: Monocular 3D Detection in Perspective Bird’s-Eye-View](https://arxiv.org/pdf/2208.09394.pdf) [`det`]
- [InterTrack: Interaction Transformer for 3D Multi-Object Tracking](https://arxiv.org/pdf/2208.08041.pdf) [`tracking`]
- [An Empirical Study of Pseudo-Labeling for Image-based 3D Object Detection](https://arxiv.org/pdf/2208.07137.pdf) [`det`]
- [RWSeg: Cross-graph Competing Random Walks for Weakly Supervised 3D Instance Segmentation](https://arxiv.org/pdf/2208.05110.pdf) [`seg`]
- [RadSegNet: A Reliable Approach to Radar Camera Fusion](https://arxiv.org/pdf/2208.03849.pdf) [`autonomous driving`]
- [Aerial Monocular 3D Object Detection](https://arxiv.org/pdf/2208.03974.pdf) [`det`; [Project](https://sjtu-magic.github.io/dataset/AM3D)]
- [TransPillars: Coarse-to-Fine Aggregation for Multi-Frame 3D Object Detection](https://arxiv.org/pdf/2208.03141.pdf) [`det`]
- [Point-McBert: A Multi-choice Self-supervised Framework for Point Cloud Pre-training](https://arxiv.org/pdf/2207.13226.pdf) [`self-supervised`]
- [MV-FCOS3D++: Multi-View Camera-Only 4D Object Detection with Pretrained Monocular Backbones](https://arxiv.org/pdf/2207.12716.pdf) [`det`; [PyTorch](https://github.com/Tai-Wang/Depth-from-Motion)]
- [On the Robustness of 3D Object Detectors](https://arxiv.org/pdf/2207.10205.pdf) [`det`]
- [Boosting 3D Object Detection via Object-Focused Image Fusion](https://arxiv.org/pdf/2207.10589.pdf) [`det`; [PyTorch](https://github.com/haoy945/DeMF)]
- [Consistency of Implicit and Explicit Features Matters for Monocular 3D Object Detection](https://arxiv.org/pdf/2207.07933.pdf) [`det`, `monocular`]
- [UniFormer: Unified Multi-view Fusion Transformer for Spatial-Temporal Representation in Bird's-Eye-View](https://arxiv.org/pdf/2207.08536.pdf) [`autonomous driving`]
- [Learning to Register Unbalanced Point Pairs](https://arxiv.org/pdf/2207.04221.pdf) [`registration`]
- [Learning Spatial and Temporal Variations for 4D Point Cloud Segmentation](https://arxiv.org/pdf/2207.04673.pdf) [`seg`]
- [MT-Net Submission to the Waymo 3D Detection Leaderboard](https://arxiv.org/pdf/2207.04781.pdf) [`det`]
- [Masked Surfel Prediction for Self-Supervised Point Cloud Learning](https://arxiv.org/pdf/2207.03111.pdf) [`self-supervised`; [Github](https://github.com/YBZh/MaskSurf)]
- [GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation](https://arxiv.org/pdf/2207.02466.pdf) [`det`]
- [Open-Vocabulary 3D Detection via Image-level Class and Debiased Cross-modal Contrastive Learning](https://arxiv.org/pdf/2207.01987.pdf) [`det`]
- [ORA3D: Overlap Region Aware Multi-view 3D Object Detection](https://arxiv.org/pdf/2207.00865.pdf) [`det`]
- [Masked Autoencoders in 3D Point Cloud Representation Learning](https://arxiv.org/pdf/2207.01545.pdf) [`self-supervised`]
- [Masked Autoencoders for Self-Supervised Learning on Automotive Point Clouds](https://arxiv.org/pdf/2207.00531.pdf) [`self-supervised`]
- [SARNet: Semantic Augmented Registration of Large-Scale Urban Point Clouds](https://arxiv.org/pdf/2206.13117.pdf) [`registration`; [PyTorch](https://github.com/WinterCodeForEverything/SARNet)]
- [HM3D-ABO: A Photo-realistic Dataset for Object-centric Multi-view 3D Reconstruction](https://arxiv.org/pdf/2206.12356.pdf) [`reconstruction`; [Github](https://github.com/zhenpeiyang/HM3D-ABO)]
- [Unseen Object 6D Pose Estimation: A Benchmark and Baselines](https://arxiv.org/pdf/2206.11808.pdf) [`pose estimation`; [Project](http://www.graspnet.net/unseen6d)]
- [LidarMutliNet: Unifying LiDAR Semantic Segmentation, 3D Object Detection, and Panoptic Segmentation in a Single Multi-task Network](https://arxiv.org/pdf/2206.11428.pdf) [`seg`, `det`]
- [Polar Parametrization for Vision-based Surround-View 3D Detection](https://arxiv.org/pdf/2206.10965.pdf) [`det`; [Github](https://github.com/hustvl/PolarDETR)]
- [Reconstruct from Top View: A 3D Lane Detection Approach based on Geometry Structure Prior](https://arxiv.org/pdf/2206.10098.pdf) [`autonomous driving`]
- [Voxel-MAE: Masked Autoencoders for Pre-training Large-scale Point Clouds](https://arxiv.org/pdf/2206.09900.pdf) [`det`; [Github](https://github.com/chaytonmin/Voxel-MAE)]
- [A Simple Baseline for BEV Perception Without LiDAR](https://arxiv.org/pdf/2206.07959.pdf) [`autonomous driving`; [PyTorch](https://github.com/aharley/simple_bev)]
- [Level 2 Autonomous Driving on a Single Device: Diving into the Devils of Openpilot](https://arxiv.org/pdf/2206.08176.pdf) [`autonomous driving`; [Github](https://github.com/OpenPerceptionX/Openpilot-Deepdive)]
- [LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection](https://arxiv.org/pdf/2206.07705.pdf) [`det`]
- [Semi-signed neural fitting for surface reconstruction from unoriented point clouds](https://arxiv.org/pdf/2206.06715.pdf) [`reconstruction`]
- [PatchComplete: Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categories](https://arxiv.org/pdf/2206.04916.pdf) [`completion`; [Project](https://yuchenrao.github.io/projects/patchComplete/patchComplete.html)]
- [VN-Transformer: Rotation-Equivariant Attention for Vector Neurons](https://arxiv.org/pdf/2206.04176.pdf) [`cls`, `motion forecasting`]
- [Depth Estimation Matters Most: Improving Per-Object Depth Estimation for Monocular 3D Detection and Tracking](https://arxiv.org/pdf/2206.03666.pdf) [`det`, `tracking`]
- [SparseDet: Towards End-to-End 3D Object Detection](https://arxiv.org/pdf/2206.00960.pdf) [`det`]
- [Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object Detection](https://arxiv.org/pdf/2205.14951.pdf) [`det`; [Github](https://github.com/kcyu2014/lidar-camera-robust-benchmark)]
- [Towards Efficient 3D Object Detection with Knowledge Distillation](https://arxiv.org/pdf/2205.15156.pdf) [`det`]
- [OpenCalib: A multi-sensor calibration toolbox for autonomous driving](https://arxiv.org/pdf/2205.14087.pdf) [`calibration`, `autonomous driving`; [Github](https://github.com/PJLab-ADG/SensorsCalibration)]
- [BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving](https://arxiv.org/pdf/2205.09743.pdf) [`autonomous driving`; [Github](https://github.com/zhangyp15/BEVerse)]
- [Continual learning on 3D point clouds with random compressed rehearsal](https://arxiv.org/pdf/2205.08013.pdf) [`continual learning`]
- [Panoptic-PHNet: Towards Real-Time and High-Precision LiDAR Panoptic Segmentation via Clustering Pseudo Heatmap](https://arxiv.org/pdf/2205.07002.pdf) [`seg`]
- [Weakly Supervised 3D Point Cloud Segmentation via Multi-Prototype Learning](https://arxiv.org/pdf/2205.03137.pdf) [`seg`]
- [Cost-Aware Comparison of LiDAR-based 3D Object Detectors](https://arxiv.org/pdf/2205.01142.pdf) [`det`]
- [Open-Set Semi-Supervised Learning for 3D Point Cloud Understanding](https://arxiv.org/pdf/2205.01006.pdf) [`cls`, `seg`]
- [Unsupervised Domain Adaptation for Monocular 3D Object Detection via Self-Training](https://arxiv.org/pdf/2204.11590.pdf) [`det`, `monocular`]
- [RangeUDF: Semantic Surface Reconstruction from 3D Point Clouds](https://arxiv.org/pdf/2204.09138.pdf) [`reconstruction`; [Github](https://github.com/vLAR-group/RangeUDF)]
- [Dynamic Point Cloud Denoising via Gradient Fields](https://arxiv.org/pdf/2204.08755.pdf) [`denoising`]
- [M^2BEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representation](https://arxiv.org/pdf/2204.05088.pdf) [`det`, `seg`; [Project](https://xieenze.github.io/projects/m2bev/)]
- [DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Indoor Semantic Segmentation](https://arxiv.org/pdf/2204.01599.pdf) [`seg`]
- [ImpDet: Exploring Implicit Fields for 3D Object Detection](https://arxiv.org/pdf/2203.17240.pdf) [`det`]
- [Learning a Structured Latent Space for Unsupervised Point Cloud Completion](https://arxiv.org/pdf/2203.15580.pdf) [`completion`]
- [Towards 3D Scene Understanding by Referring Synthetic Models](https://arxiv.org/pdf/2203.10546v1.pdf) [`transfer learning`]
- [Unsupervised Learning of 3D Semantic Keypoints with Mutual Reconstruction](https://arxiv.org/pdf/2203.10212v1.pdf) [`keypoints`]
- [Self-supervised Point Cloud Completion on Real Traffic Scenes via Scene-concerned Bottom-up Mechanism](https://arxiv.org/pdf/2203.10569v1.pdf) [`completion`]
- [FUTR3D: A Unified Sensor Fusion Framework for 3D Detection](https://arxiv.org/pdf/2203.10642v1.pdf) [`det`; [PyTorch](https://github.com/Tsinghua-MARS-Lab/futr3d)]
- [3DAC: Learning Attribute Compression for Point Clouds](https://arxiv.org/pdf/2203.09931v1.pdf) [`compression`]
- [Deep learning for radar data exploitation of autonomous vehicle](https://arxiv.org/pdf/2203.08038.pdf) [`radar`, `autonomous vehicle`]
- [LiDAR-based 4D Panoptic Segmentation via Dynamic Shifting Network](https://arxiv.org/pdf/2203.07186.pdf) [`seg`]
- [CVFNet: Real-time 3D Object Detection by Learning Cross View Features](https://arxiv.org/pdf/2203.06585.pdf) [`det`]
- [PD-Flow: A Point Cloud Denoising Framework with Normalizing Flows](https://arxiv.org/pdf/2203.05940.pdf) [`denoising`]
- [An Empirical Investigation of 3D Anomaly Detection and Segmentation](https://arxiv.org/pdf/2203.05550.pdf) [`anomaly detection`; [PyTorch](https://github.com/eliahuhorwitz/3D-ADS)]
- [A Lightweight and Detector-free 3D Single Object Tracker on Point Clouds](https://arxiv.org/pdf/2203.04232.pdf) [`tracking`]
- [DisARM: Displacement Aware Relation Module for 3D Detection](https://arxiv.org/pdf/2203.01152.pdf) [`det`]
- [Dense Voxel Fusion for 3D Object Detection](https://arxiv.org/pdf/2203.00871.pdf) [`det`]
- [PointMatch: A Consistency Training Framework for Weakly Supervised Semantic Segmentation of 3D Point Clouds](https://arxiv.org/pdf/2202.10705.pdf) [`seg`]
- [Distillation with Contrast is All You Need for Self-Supervised Point Cloud Representation Learning](https://arxiv.org/pdf/2202.04241.pdf) [`self-supervised`]
- [Edge-Selective Feature Weaving for Point Cloud Matching](https://arxiv.org/pdf/2202.02149.pdf) [`correspondence`; [PyTorch-lightning](https://github.com/yanarin/ESFW)]
- [Neighborhood-aware Geometric Encoding Network for Point Cloud Registration](https://arxiv.org/pdf/2201.12094v1.pdf) [`registration`; [PyTorch](https://github.com/zhulf0804/NgeNet)]
- [Boosting Monocular Depth Estimation with Sparse Guided Points](https://arxiv.org/pdf/2202.01470.pdf) [`monocular`, `depth estimation`; [Github](https://github.com/aim-uofa/AdelaiDepth)]
- [Trajectory Forecasting from Detection with Uncertainty-Aware Motion Encoding](https://arxiv.org/pdf/2202.01478.pdf) [`autonomous platforms`]
- [TPC: Transformation-Specific Smoothing for Point Cloud Models](https://arxiv.org/pdf/2201.12733v1.pdf) [`attack`]
- [Self-supervised Point Cloud Registration with Deep Versatile Descriptors](https://arxiv.org/pdf/2201.10034.pdf) [`registration`]
- [Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision](https://arxiv.org/pdf/2201.02963.pdf) [`seg`]
## 2021
- ICCV
- [erception-Aware Multi-Sensor Fusion for 3D LiDAR Semantic Segmentation](https://openaccess.thecvf.com/content/ICCV2021/papers/Zhuang_Perception-Aware_Multi-Sensor_Fusion_for_3D_LiDAR_Semantic_Segmentation_ICCV_2021_paper.pdf) [`seg`]
- [Differentiable Convolution Search for Point Cloud Processing](https://arxiv.org/pdf/2108.12856.pdf) [`cls`, `seg`]
- [MVTN: Multi-View Transformation Network for 3D Shape Recognition](https://arxiv.org/pdf/2011.13244.pdf) [`cls`, `retrieval`; [PyTorch](https://github.com/ajhamdi/MVTN)]
- [Self-Supervised Pretraining of 3D Features on any Point-Cloud](https://arxiv.org/pdf/2101.02691.pdf) [`self-supervised`; [PyTorch](https://github.com/facebookresearch/DepthContrast)]
- [MGNet: Monocular Geometric Scene Understanding for Autonomous Driving](https://openaccess.thecvf.com/content/ICCV2021/papers/Schon_MGNet_Monocular_Geometric_Scene_Understanding_for_Autonomous_Driving_ICCV_2021_paper.pdf) [`autonomous driving`; [PyTorch](https://github.com/markusschoen/MGNet)]
- [FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection](https://arxiv.org/pdf/2104.10956.pdf) [`monocular`, `det`; [mmdet3d](https://github.com/open-mmlab/mmdetection3d)]
- [Progressive Seed Generation Auto-encoder for Unsupervised Point Cloud Learning](https://arxiv.org/pdf/2112.05213.pdf) [`unsupervised`]
- [Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation](https://arxiv.org/pdf/2110.08188.pdf) [`seg`]
- [Pyramid Point Cloud Transformer for Large-Scale Place Recognition](https://openaccess.thecvf.com/content/ICCV2021/papers/Hui_Pyramid_Point_Cloud_Transformer_for_Large-Scale_Place_Recognition_ICCV_2021_paper.pdf) [`place recognition`; [Github](https://github.com/fpthink/PPT-Net)]
- [Distinctiveness oriented Positional Equilibrium for Point Cloud Registration](https://openaccess.thecvf.com/content/ICCV2021/papers/Min_Distinctiveness_Oriented_Positional_Equilibrium_for_Point_Cloud_Registration_ICCV_2021_paper.pdf) [`registration`]
- [Feature Interactive Representation for Point Cloud Registration](https://openaccess.thecvf.com/content/ICCV2021/papers/Wu_Feature_Interactive_Representation_for_Point_Cloud_Registration_ICCV_2021_paper.pdf) [`registration`]
- [DeepPRO: Deep Partial Point Cloud Registration of Objects](https://openaccess.thecvf.com/content/ICCV2021/papers/Lee_DeepPRO_Deep_Partial_Point_Cloud_Registration_of_Objects_ICCV_2021_paper.pdf) [`registration`]
- [LSG-CPD: Coherent Point Drift with Local Surface Geometry for Point Cloud Registration](https://arxiv.org/pdf/2103.15039.pdf) [`registration`; [matlab](https://github.com/ChirikjianLab/LSG-CPD)]
- [Provably Approximated Point Cloud Registration](https://openaccess.thecvf.com/content/ICCV2021/papers/Jubran_Provably_Approximated_Point_Cloud_Registration_ICCV_2021_paper.pdf) [`registration`]
- [Point Transformer](https://arxiv.org/pdf/2012.09164.pdf) [`seg`, `cls`; [PyTorch-unofficial](https://github.com/lucidrains/point-transformer-pytorch)]
- [Point Cloud Augmentation with Weighted Local Transformations](https://arxiv.org/pdf/2110.05379.pdf) [`augmentation`; [PyTorch](https://github.com/mlvlab/PointWOLF)]
- [PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Clouds](https://arxiv.org/pdf/2110.01269.pdf) [`registration`; [PyTorch](https://github.com/valeoai/PCAM)]
- [An End-to-End Transformer Model for 3D Object Detection](https://arxiv.org/pdf/2109.08141.pdf) [`det`; [PyTorch](https://github.com/facebookresearch/3detr)]
- [Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration](https://arxiv.org/pdf/2109.06619.pdf) [`registration`; [Github](https://github.com/Jiang-HB/CEMNet)]
- [Deep Hough Voting for Robust Global Registration](https://arxiv.org/pdf/2109.04310.pdf) [`registration`; [PyTorch](https://github.com/junha-l/DHVR)]
- [P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching](https://arxiv.org/pdf/2103.01055.pdf) [`matching`]
- [Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection](https://arxiv.org/pdf/2109.02499.pdf) [`det`]
- [Voxel Transformer for 3D Object Detection](https://arxiv.org/pdf/2109.02497.pdf) [`det`]
- [Learning Inner-Group Relations on Point Clouds](https://arxiv.org/pdf/2108.12468.pdf) [`cls`, `seg`]
- [Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds](https://arxiv.org/pdf/2109.00179.pdf) [`self-supervised`; [Github](https://github.com/yichen928/STRL)]
- [4D-Net for Learned Multi-Modal Alignment](https://arxiv.org/pdf/2109.01066.pdf) [`det`]
- [AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection](https://arxiv.org/pdf/2108.11127.pdf) [`monocular`, `det`; [Github](https://github.com/zongdai/AutoShape)]
- [A Robust Loss for Point Cloud Registration](https://arxiv.org/pdf/2108.11682.pdf) [`registration`]
- [OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration](https://arxiv.org/pdf/2103.00937.pdf) [`registration`]
- [Improving 3D Object Detection with Channel-wise Transformer](https://arxiv.org/pdf/2108.10723.pdf) [`det`; [Github](https://github.com/hlsheng1/CT3D)]
- [Voxel-based Network for Shape Completion by Leveraging Edge Generation](https://arxiv.org/pdf/2108.09936v1.pdf) [`completion`; [Github](https://github.com/xiaogangw/VE-PCN)]
- [Exploring Simple 3D Multi-Object Tracking for Autonomous Driving](https://arxiv.org/pdf/2108.10312.pdf) [`tracking`]
- [ME-PCN: Point Completion Conditioned on Mask Emptiness](https://arxiv.org/pdf/2108.08187.pdf) [`completion`]
- [Deep Hybrid Self-Prior for Full 3D Mesh Generation](https://arxiv.org/pdf/2108.08017.pdf) [`generation`]
- [Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimation](https://arxiv.org/pdf/2108.08829.pdf) [`monocular`, `depth`; [Github](https://github.com/hyBlue/FSRE-Depth)]
- [StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimation](https://arxiv.org/pdf/2108.08574.pdf) [`monocular`, `depth`; [PyTorch](https://github.com/SJTU-ViSYS/StructDepth)]
- [Vis2Mesh: Efficient Mesh Reconstruction from Unstructured Point Clouds of Large Scenes with Learned Virtual View Visibility](https://arxiv.org/pdf/2108.08378.pdf) [`reconstruction`; [Github](https://github.com/GDAOSU/vis2mesh)]
- [Multi-view 3D Reconstruction with Transformer](https://arxiv.org/pdf/2103.12957.pdf) [`reconstruction`]
- [PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers](https://arxiv.org/pdf/2108.08839.pdf) [`completion`; [PyTorch](https://github.com/yuxumin/PoinTr)]
- [Adaptive Graph Convolution for Point Cloud Analysis](https://arxiv.org/pdf/2108.08035.pdf) [`cls`, `seg`; [PyTorch](https://github.com/hrzhou2/AdaptConv-master)]
- [RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detection](https://arxiv.org/pdf/2108.07794.pdf) [`det`]
- [Self-supervised Monocular Depth Estimation for All Day Images using Domain Separation](https://arxiv.org/pdf/2108.07628.pdf) [`monocular`, `depth`; [Github](https://github.com/LINA-lln/ADDS-DepthNet)]
- [Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks](https://arxiv.org/pdf/2108.07478.pdf) [`seg`; [Github](https://github.com/Gorilla-Lab-SCUT/SSTNet)]
- [Is Pseudo-Lidar needed for Monocular 3D Object detection?](https://arxiv.org/pdf/2108.06417.pdf) [`monocular`, `det`; [Github](https://github.com/TRI-ML/dd3d)]
- [Towards Efficient Point Cloud Graph Neural Networks Through Architectural Simplification](https://arxiv.org/pdf/2108.06317.pdf)
- [Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis](https://arxiv.org/pdf/2105.01288.pdf) [`cls`, `seg`; [Github](https://github.com/tiangexiang/CurveNet)]
- [AdaFit: Rethinking Learning-based Normal Estimation on Point Clouds](https://arxiv.org/pdf/2108.05836.pdf) [`normal estimation`; [Github](https://github.com/Runsong123/AdaFit/tree/main)]
- [Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather](https://arxiv.org/pdf/2108.05249.pdf) [`det`; [Github](https://github.com/MartinHahner/LiDAR_fog_sim)]
- [Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds](https://arxiv.org/pdf/2108.04728.pdf) [`tracking`; [Github](https://github.com/Ghostish/BAT)]
- [SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer](https://arxiv.org/pdf/2108.04444.pdf) [`completion`; [Github](https://github.com/AllenXiangX/SnowflakeNet)]
- [DRINet: A Dual-Representation Iterative Learning Network for Point Cloud Segmentation](https://arxiv.org/pdf/2108.04023.pdf) [`seg`]
- [RangeDet: In Defense of Range View for LiDAR-based 3D Object Detection](https://arxiv.org/pdf/2103.10039.pdf) [`det`; [Github](https://github.com/TuSimple/RangeDet)]
- [Hierarchical Aggregation for 3D Instance Segmentation](https://arxiv.org/pdf/2108.02350.pdf) [`seg`; [Github](https://github.com/hustvl/HAIS)]
- [Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentation](https://arxiv.org/pdf/2107.14724.pdf) [`seg`; [Github](https://github.com/leolyj/DsCML)]
- [Group-Free 3D Object Detection via Transformers](https://arxiv.org/pdf/2104.00678.pdf) [`det`; [PyTorch](https://github.com/zeliu98/Group-Free-3D)]
- [VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation](https://arxiv.org/pdf/2107.13824.pdf) [`seg`; [Github](https://github.com/hzykent/VMNet)]
- [Learning with Noisy Labels for Robust Point Cloud Segmentation](https://arxiv.org/pdf/2107.14230.pdf) [`seg`; [Github](https://github.com/pleaseconnectwifi/PNAL)]
- [Geometry Uncertainty Projection Network for Monocular 3D Object Detection](https://arxiv.org/pdf/2107.13774.pdf) [`det`, `monocular`]
- [ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation](https://arxiv.org/pdf/2107.11769.pdf) [`seg`; [PyTorch](https://github.com/tsunghan-mama/ReDAL)]
- [Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency](https://arxiv.org/pdf/2107.11355.pdf) [`det`; [OpenPCDet](https://github.com/Jasonkks/mlcnet)]
- [Unsupervised Point Cloud Pre-Training via View-Point Occlusion, Completion](https://arxiv.org/pdf/2010.01089.pdf) [`pre-training`; [Github](https://github.com/hansen7/OcCo)]
- [HRegNet: A Hierarchical Network for Large-scale Outdoor LiDAR Point Cloud Registration](https://arxiv.org/pdf/2107.11992.pdf) [`registration`; [PyTorch](https://github.com/ispc-lab/HRegNet)]
- [Score-Based Point Cloud Denoising](https://arxiv.org/pdf/2107.10981.pdf) [`denoising`]
- [Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows](https://arxiv.org/pdf/2107.13788.pdf) [`monocular`, `pose`; [Github](https://github.com/twehrbein/Probabilistic-Monocular-3D-Human-Pose-Estimation-with-Normalizing-Flows)]
- [A Technical Survey and Evaluation of Traditional Point Cloud Clustering Methods for LiDAR Panoptic Segmentation](https://arxiv.org/pdf/2108.09522.pdf) [`seg`; [Github](https://github.com/placeforyiming/ICCVW21-LiDAR-Panoptic-Segmentation-TradiCV-Survey-of-Point-Cloud-Cluster)]
- [The Devil is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detection](https://arxiv.org/pdf/2112.14023.pdf) [`monocular`, `det`]
- CVPR
- [Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling](https://arxiv.org/pdf/2111.14819.pdf) [`self-supervised`; [PyTorch](https://github.com/lulutang0608/Point-BERT)]
- [Self-Supervised Learning on 3D Point Clouds by Learning Discrete Generative Models](https://openaccess.thecvf.com/content/CVPR2021/papers/Eckart_Self-Supervised_Learning_on_3D_Point_Clouds_by_Learning_Discrete_Generative_CVPR_2021_paper.pdf) [`self-supervised`]
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation](https://arxiv.org/pdf/2011.10033.pdf) [`seg`; [PyTorch](https://github.com/xinge008/Cylinder3D)]
- [PointAugmenting: Cross-Modal Augmentation for 3D Object Detection](https://openaccess.thecvf.com/content/CVPR2021/papers/Wang_PointAugmenting_Cross-Modal_Augmentation_for_3D_Object_Detection_CVPR_2021_paper.pdf) [`det`]
- [PVGNet: A Bottom-Up One-Stage 3D Object Detector with Integrated Multi-Level Features](https://openaccess.thecvf.com/content/CVPR2021/papers/Miao_PVGNet_A_Bottom-Up_One-Stage_3D_Object_Detector_With_Integrated_Multi-Level_CVPR_2021_paper.pdf) [`det`]
- [MetaSets: Meta-Learning on Point Sets for Generalizable Representations](https://openaccess.thecvf.com/content/CVPR2021/papers/Huang_MetaSets_Meta-Learning_on_Point_Sets_for_Generalizable_Representations_CVPR_2021_paper.pdf) [`domain`]
- [LiDAR-based Panoptic Segmentation via Dynamic Shifting Network](https://openaccess.thecvf.com/content/CVPR2021/papers/Hong_LiDAR-Based_Panoptic_Segmentation_via_Dynamic_Shifting_Network_CVPR_2021_paper.pdf) [`seg`; [PyTorch](https://github.com/hongfz16/DS-Net)]
- [PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Paths](https://arxiv.org/pdf/2012.03408.pdf) [`completion`; [PyTorch](https://github.com/diviswen/PMP-Net)]
- [CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds](https://arxiv.org/pdf/2012.15638.pdf) [`correspondence`; [PyTorch-lightning](https://github.com/ZENGYIMING-EAMON/CorrNet3D)]
- [StickyPillars: Robust and Efficient Feature Matching on Point Clouds using Graph Neural Networks](https://openaccess.thecvf.com/content/CVPR2021/papers/Fischer_StickyPillars_Robust_and_Efficient_Feature_Matching_on_Point_Clouds_Using_CVPR_2021_paper.pdf) [`registration`]
- [To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernels](https://arxiv.org/pdf/2106.13381.pdf) [`det`]
- [RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection](https://arxiv.org/pdf/2106.13365.pdf) [`det`]
- [Point Cloud Upsampling via Disentangled Refinement](https://arxiv.org/pdf/2106.04779.pdf) [`upsampling`; [Github](https://github.com/liruihui/Dis-PU)]
- [Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning](https://arxiv.org/pdf/2105.10203.pdf) [`seg`]
- [Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts](https://arxiv.org/pdf/2012.09165.pdf) [`seg`; [PyTorch](https://github.com/facebookresearch/ContrastiveSceneContexts)]
- [PU-GCN: Point Cloud Upsampling using Graph Convolutional Networks](https://arxiv.org/pdf/1912.03264.pdf) [`upsampling`; [Tensorflow](https://github.com/guochengqian/PU-GCN)]
- [Self-Point-Flow: Self-Supervised Scene Flow Estimation from Points Clouds with Optimal Transport and Random Walk](https://arxiv.org/pdf/2105.08248.pdf) [`scene flow`]
- [SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction from Video Data](https://arxiv.org/pdf/2105.08612.pdf) [`reconstruction`]
- [HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embedding](https://arxiv.org/pdf/2105.07751.pdf) [`scene flow`]
- [3D Spatial Recognition without Spatially Labeled 3D](https://arxiv.org/pdf/2105.06461.pdf) [`det`, `seg`]
- [LASR: Learning Articulated Shape Reconstruction from a Monocular Video](https://arxiv.org/pdf/2105.02976.pdf) [`reconstruction`, `monocular`]
- [VoxelContext-Net: An Octree based Framework for Point Cloud Compression](https://arxiv.org/pdf/2105.02158.pdf) [`compression`]
- [Unsupervised 3D Shape Completion through GAN Inversion](https://arxiv.org/pdf/2104.13366.pdf) [`completion`; [PyTorch](https://junzhezhang.github.io/projects/ShapeInversion/)]
- [KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control](https://arxiv.org/pdf/2104.11224.pdf) [[Github](https://github.com/tomasjakab/keypoint_deformer/)]
- [Multi-Modal Fusion Transformer for End-to-End Autonomous Driving](https://arxiv.org/pdf/2104.09224.pdf) [`autonomous driving`; [PyTorch](https://github.com/autonomousvision/transfuser)]
- [Self-Supervised Pillar Motion Learning for Autonomous Driving](https://arxiv.org/pdf/2104.08683.pdf) [`autonomous driving`; [Github](https://github.com/qcraftai/pillar-motion)]
- [Variational Relational Point Completion Network](https://arxiv.org/pdf/2104.10154.pdf) [`completion`; [PyTorch](https://github.com/paul007pl/VRCNet)]
- [Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds](https://arxiv.org/pdf/2104.06114.pdf) [`det`; [Github](https://github.com/cheng052/BRNet)]
- [RPSRNet: End-to-End Trainable Rigid Point Set Registration Network using Barnes-Hut 2D-Tree Representation](https://arxiv.org/pdf/2104.05328.pdf) [`registration`]
- [Objects are Different: Flexible Monocular 3D Object Detection](https://arxiv.org/pdf/2104.02323.pdf) [`det`; [Github](https://github.com/zhangyp15/MonoFlex)]
- [FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point Clouds](https://arxiv.org/pdf/2104.00798.pdf) [`scene flow`]
- [HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detection](https://arxiv.org/pdf/2104.00902.pdf) [`det`]
- [Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation](https://arxiv.org/pdf/2103.14962.pdf) [`seg`; [PyTorch](https://github.com/edwardzhou130/Panoptic-PolarNet)]
- [ReAgent: Point Cloud Registration using Imitation and Reinforcement Learning](https://arxiv.org/pdf/2103.15231.pdf) [`registration`; [PyTorch](https://github.com/dornik/reagent)]
- [UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering](https://arxiv.org/pdf/2102.11870.pdf) [`registration`; [PyTorch](https://github.com/mbanani/unsupervisedRR)]
- [LiDAR R-CNN: An Efficient and Universal 3D Object Detector](https://arxiv.org/pdf/2103.15297.pdf) [`det`; [Github](https://github.com/TuSimple/LiDAR_RCNN)]
- [Equivariant Point Network for 3D Point Cloud Analysis](https://arxiv.org/pdf/2103.14147.pdf) [[Github](https://github.com/nintendops/EPN_PointCloud)]
- [PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds](https://arxiv.org/pdf/2103.14635.pdf) [`cls`, `det`; [Github](https://github.com/CVMI-Lab/PAConv)]
- [Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection](https://arxiv.org/pdf/2103.16470.pdf) [`det`; [Github](https://github.com/fudan-zvg/DDMP)]
- [Delving into Localization Errors for Monocular 3D Object Detection](https://arxiv.org/pdf/2103.16237.pdf) [`det`; [Github](https://github.com/xinzhuma/monodle)]
- [M3DSSD: Monocular 3D Single Stage Object Detector](https://arxiv.org/pdf/2103.13164.pdf) [`det`; [Github](https://github.com/mumianyuxin/M3DSSD)]
- [Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding](https://arxiv.org/pdf/2103.07838.pdf) [`completion`]
- [Monte Carlo Scene Search for 3D Scene Understanding](https://arxiv.org/pdf/2103.07969.pdf)
- [Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion](https://arxiv.org/pdf/2103.07074.pdf) [`seg`; [Github](https://github.com/ShiQiu0419/BAAF-Net)]
- [PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency](https://arxiv.org/pdf/2103.05465.pdf) [`registration`; [PyTorch](https://github.com/XuyangBai/PointDSC)]
- [ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection](https://arxiv.org/pdf/2103.05346.pdf) [`det`; [OpenPCDet](https://github.com/CVMI-Lab/ST3D)]
- [Robust Point Cloud Registration Framework Based on Deep Graph Matching](https://arxiv.org/pdf/2103.04256.pdf) [`registration`; [Github](https://github.com/fukexue/RGM)]
- [RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction](https://arxiv.org/pdf/2011.14744.pdf) [`reconstruction`]
- [MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization](https://arxiv.org/pdf/2101.06605.pdf) [`motion analysis`; [Github](https://github.com/huangjh-pub/multibody-sync)]
- [TPCN: Temporal Point Cloud Networks for Motion Forecasting](https://arxiv.org/pdf/2103.03067.pdf) [`motion forecasting`]
- [Self-supervised Geometric Perception](https://arxiv.org/pdf/2103.03114.pdf) [`self-supervised`; [Github](https://github.com/theNded/SGP)]
- [PointGuard: Provably Robust 3D Point Cloud Classification](https://arxiv.org/pdf/2103.03046.pdf) [`cls`]
- [Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos](None)
- [SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud](None) [`det`; [Github](https://github.com/Vegeta2020/SE-SSD)]
- [Center-based 3D Object Detection and Tracking](https://arxiv.org/pdf/2006.11275.pdf) [`det`, `tracking`; [PyTorch](https://github.com/tianweiy/CenterPoint)]
- [3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection](https://arxiv.org/pdf/2012.04355.pdf) [`det`; [PyTorch](https://github.com/thu17cyz/3DIoUMatch)]
- [Style-based Point Generator with Adversarial Rendering for Point Cloud Completion](https://arxiv.org/pdf/2103.02535.pdf) [`completion`]
- [FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation](https://arxiv.org/pdf/2103.02242.pdf) [`pose estimation`; [Github](https://github.com/ethnhe/FFB6D)]
- [Diffusion Probabilistic Models for 3D Point Cloud Generation](https://arxiv.org/pdf/2103.01458.pdf) [`generation`; [Github](https://github.com/luost26/diffusion-point-cloud)]
- [GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation](https://arxiv.org/pdf/2102.12145.pdf) [`pose estimation`; [Github](https://github.com/THU-DA-6D-Pose-Group/GDR-Net)]
- [PCLs: Geometry-aware Neural Reconstruction of 3D Pose with Perspective Crop Layers](https://arxiv.org/pdf/2011.13607.pdf) [`reconstruction`]
- [PREDATOR: Registration of 3D Point Clouds with Low Overlap](https://arxiv.org/pdf/2011.13005.pdf) [`registration`; [PyTorch](https://github.com/ShengyuH/OverlapPredator)]
- [SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration](https://arxiv.org/pdf/2011.12149.pdf) [`registration`; [Github](https://github.com/QingyongHu/SpinNet)]
- [Categorical Depth Distribution Network for Monocular 3D Object Detection](https://arxiv.org/pdf/2103.01100.pdf) [`det`]
- [Multimodal Motion Prediction with Stacked Transformers](https://arxiv.org/pdf/2103.11624.pdf) [`motion prediction`; [Github](https://github.com/decisionforce/mmTransformer)]
- [GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection](https://arxiv.org/pdf/2103.17202.pdf) [`det`; [PyTorch](https://github.com/abhi1kumar/groomed_nms)]
- [Model-based 3D Hand Reconstruction via Self-Supervised Learning](https://arxiv.org/abs/2103.11703) [`reconstruction`]
- [MonoRUn: Monocular 3D Object Detection by Self-Supervised Reconstruction and Uncertainty Propagation](https://arxiv.org/pdf/2103.12605.pdf) [`det`; [Github](https://github.com/tjiiv-cprg/MonoRUn)]
- [Deep Implicit Moving Least-Squares Functions for 3D Reconstruction](https://arxiv.org/pdf/2103.12266.pdf) [`reconstruction`; [Tensorflow](https://github.com/Andy97/DeepMLS)]
- [Skeleton Merger: an Unsupervised Aligned Keypoint Detector](https://arxiv.org/pdf/2103.10814.pdf) [`keypoint`; [PyTorch](https://github.com/eliphatfs/SkeletonMerger)]
- [Single Image Depth Prediction with Wavelet Decomposition](https://arxiv.org/pdf/2106.02022.pdf) [`depth`; [PyTorch](https://github.com/nianticlabs/wavelet-monodepth)]
- [3D Shape Generation with Grid-based Implicit Functions](https://arxiv.org/pdf/2107.10607.pdf) [`generation`]
- [Joint Learning of 3D Shape Retrieval and Deformation](https://arxiv.org/pdf/2101.07889.pdf) [`generation`]
- Others
- [PRA-Net: Point Relation-Aware Network for 3D Point Cloud Analysis](https://arxiv.org/pdf/2112.04903.pdf) [`cls`, `seg`; [PyTorch](https://github.com/XiwuChen/PRA-Net); TIP]
- [PCT: Point Cloud Transformer](https://arxiv.org/pdf/2012.09688.pdf) [`cls`, `seg`, `normal estimation`; [Jittor](https://github.com/MenghaoGuo/PCT); CVM]
- [DeepUME: Learning the Universal Manifold Embedding for Robust Point Cloud Registration](https://arxiv.org/pdf/2112.09938.pdf) [`registration`; [PyTorch](https://github.com/langnatalie/DeepUME); BMVC]
- [On Automatic Data Augmentation for 3D Point Cloud Classification](https://arxiv.org/pdf/2112.06029.pdf) [`augmentation`, `cls`; BMVC]
- [Self-Supervised Point Cloud Completion via Inpainting](https://arxiv.org/pdf/2111.10701.pdf) [`completion`; BMVC]
- [Two Heads are Better than One: Geometric-Latent Attention for Point Cloud Classification and Segmentation](https://arxiv.org/pdf/2111.00231.pdf) [`cls`, `seg`; BMVC]
- [3D Object Tracking with Transformer](https://arxiv.org/pdf/2110.14921.pdf) [`tracking`; [Github](https://github.com/3bobo/lttr); BMVC]
- [Cascading Feature Extraction for Fast Point Cloud Registration](https://arxiv.org/pdf/2110.12204.pdf) [`registration`; BMVC]
- [PolarStream: Streaming Lidar Object Detection and Segmentation with Polar Pillars](https://arxiv.org/pdf/2106.07545.pdf) [`det`, `seg`; [PyTorch](https://github.com/motional/polarstream); NeurIPS]
- [Revisiting 3D Object Detection From an Egocentric Perspective](https://arxiv.org/pdf/2112.07787.pdf) [`det`; NeurIPS]
- [Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion](https://openreview.net/pdf/e6d90c93c4adcc32b69c557d71159704b043ed4b.pdf) [`completion`; [PyTorch](https://github.com/wutong16/Density_aware_Chamfer_Distance); NeurIPS]
- [Multimodal Virtual Point 3D Detection](https://arxiv.org/pdf/2111.06881.pdf) [`det`; [PyTorch](https://github.com/tianweiy/MVP); NeurIPS]
- [3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds](https://arxiv.org/pdf/2111.04426.pdf) [`tracking`; [Github](https://github.com/fpthink/V2B); NeurIPS]
- [Voxel-based 3D Detection and Reconstruction of Multiple Objects from a Single Image](https://arxiv.org/pdf/2111.03098.pdf) [`monocular`, `det`, `reconstruction`; NeurIPS]
- [Accurate Point Cloud Registration with Robust Optimal Transport](https://arxiv.org/pdf/2111.00648.pdf) [`registration`; [Github](https://github.com/uncbiag/robot); NeurIPS]
- [CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration](https://arxiv.org/pdf/2110.14076.pdf) [`registration`; [PyTorch](https://github.com/haoyu94/Coarse-to-fine-correspondences); NeurIPS]
- [Shape registration in the time of transformers](https://arxiv.org/pdf/2106.13679.pdf) [`registration`; `non-rigid`; NeurIPS]
- [Object DGCNN: 3D Object Detection using Dynamic Graphs](https://arxiv.org/pdf/2110.06923.pdf) [`det`; [Github](https://github.com/WangYueFt/detr3d); NeurIPS]
- [Multi-modal Trajectory Prediction for Autonomous Driving with Semantic Map and Dynamic Graph Attention Network](https://arxiv.org/pdf/2103.16273.pdf) [`autonomous driving`; NeurIPS]
- [Probabilistic and Geometric Depth: Detecting Objects in Perspective](https://proceedings.mlr.press/v164/wang22i/wang22i.pdf) [`det`; [mmdet3d](https://github.com/open-mmlab/mmdetection3d); CoRL]
- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://arxiv.org/pdf/2110.06922.pdf) [`det`; [Github](https://github.com/WangYueFt/detr3d); CoRL]
- [Self-supervised Point Cloud Prediction Using 3D Spatio-temporal Convolutional Networks](https://arxiv.org/pdf/2110.04076.pdf) [`autonomous driving`; [Github](https://github.com/PRBonn/point-cloud-prediction); CoRL]
- [Semi-supervised 3D Object Detection via Temporal Graph Neural Networks](https://arxiv.org/pdf/2202.00182.pdf) [`det`]
- [GASCN: Graph Attention Shape Completion Network](https://arxiv.org/pdf/2201.07937v1.pdf) [`completion`; 3DV]
- [DurLAR: A High-Fidelity 128-Channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-Modal Autonomous Driving Applications](http://dro.dur.ac.uk/34293/1/34293.pdf?DDD4+DDC116+DDD280+vbdv77) [`monocular`, `autonomous driving`; [Github](https://github.com/l1997i/DurLAR); 3DV]
- [Learning Iterative Robust Transformation Synchronization](https://arxiv.org/pdf/2111.00728.pdf) [`transformation synchronization`; [Github](https://github.com/yewzijian/MultiReg); 3DV]
- [DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction](https://arxiv.org/pdf/2110.08636.pdf) [`correspondence`; [PyTorch](https://github.com/dvirginz/DPC); 3DV]
- [DeepBBS: Deep Best Buddies for Point Cloud Registration](https://arxiv.org/pdf/2110.03016.pdf) [`registration`; [PyTorch](https://github.com/itanhe/DeepBBS); 3DV]
- [3D Point Cloud Registration with Multi-Scale Architecture and Self-supervised Fine-tuning](https://arxiv.org/pdf/2103.14533.pdf) [`registration`; [Github](https://github.com/humanpose1/MS-SVConv); 3DV]
- [Investigating Attention Mechanism in 3D Point Cloud Object Detection](https://arxiv.org/pdf/2108.00620.pdf) [`det`; [Github](https://github.com/ShiQiu0419/attentions_in_3D_detection); 3DV]
- [Similarity-Aware Fusion Network for 3D Semantic Segmentation](https://arxiv.org/pdf/2107.01579.pdf) [`seg`; [Github](https://github.com/lqzhao/SAFNet); IROS]
- [Model-free Vehicle Tracking and State Estimation in Point Cloud Sequences](https://arxiv.org/pdf/2103.06028.pdf) [`autonomous driving`; [Github](https://github.com/TuSimple/LiDAR_SOT); IROS]
- [Part-Aware Data Augmentation for 3D Object Detection in Point Cloud](https://arxiv.org/pdf/2007.13373.pdf) [`det`, `augmentation`; [PyTorch](https://github.com/sky77764/pa-aug.pytorch)]
- [Cross-modality Discrepant Interaction Network for RGB-D Salient Object Detection](https://arxiv.org/pdf/2108.01971.pdf) [`det`; ACM MM]
- [From Voxel to Point: IoU-guided 3D Object Detection for Point Cloud with Voxel-to-Point Decoder](https://arxiv.org/pdf/2108.03648.pdf) [`det`; [Github](https://github.com/jialeli1/From-Voxel-to-Point); ACM MM]
- [Anchor-free 3D Single Stage Detector with Mask-Guided Attention for Point Cloud](https://arxiv.org/pdf/2108.03634.pdf) [`det`; [Github](https://github.com/jialeli1/MGAF-3DSSD); ACM MM]
- [Hierarchical View Predictor: Unsupervised 3D Global Feature Learning through Hierarchical Prediction among Unordered Views](https://arxiv.org/pdf/2108.03743.pdf) [`unsupervised`; ACM MM]
- [SSPU-Net: Self-Supervised Point Cloud Upsampling via Differentiable Rendering](https://arxiv.org/pdf/2108.00454.pdf) [`upsampling`; [Github](https://github.com/Avlon/SSPU-Net); ACM MM]
- [Self-Contrastive Learning with Hard Negative Sampling for Self-supervised Point Cloud Learning](https://arxiv.org/pdf/2107.01886.pdf) [`self-supervised`; ACM MM]
- [Neighbor-Vote: Improving Monocular 3D Object Detection through Neighbor Distance Voting](https://arxiv.org/pdf/2107.02493.pdf) [`monocular`, `det`; ACM MM]
- [Fast and Robust Registration of Partially Overlapping Point Clouds](https://arxiv.org/pdf/2112.09922.pdf) [`registration`; [PyTorch](https://github.com/eduardohenriquearnold/fastreg); RAL]
- [Graph-Guided Deformation for Point Cloud Completion](https://arxiv.org/pdf/2112.01840.pdf) [`completion`; RAL]
- [GIDSeg: Learning 3D Segmentation from Sparse Annotations via Hierarchical Descriptors](https://arxiv.org/pdf/2105.12885.pdf) [`seg`; RAL]
- [Planning with Learned Dynamic Model for Unsupervised Point Cloud Registration](https://arxiv.org/pdf/2108.02613.pdf) [`registration`; IJCAI]
- [PointLIE: Locally Invertible Embedding for Point Cloud Sampling and Recovery](https://arxiv.org/pdf/2104.14769.pdf) [`sampling`; [Github](https://github.com/zwb0/PointLIE); IJCAI]
- [Unsupervised Shape Completion via Deep Prior in the Neural Tangent Kernel Perspective](https://arxiv.org/pdf/2104.09023.pdf) [`completion`; TOG]
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception](https://arxiv.org/pdf/2109.05441.pdf) [`seg`, `det`; [PyTorch](https://github.com/xinge008/Cylinder3D); TPAMI]
- [Point Cloud Instance Segmentation with Semi-supervised Bounding-Box Mining](https://arxiv.org/pdf/2111.15210.pdf) [`seg`; TPAMI]
- [Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling](https://arxiv.org/pdf/2107.02389.pdf) [`seg`; TPAMI]
- [Fast and Robust Iterative Closest Point](https://arxiv.org/pdf/2007.07627.pdf) [`registration`; [Github](https://github.com/yaoyx689/Fast-Robust-ICP); TPAMI]
- [MonoGRNet: A General Framework for Monocular 3D Object Detection](https://arxiv.org/pdf/2104.08797.pdf) [`monocular`, `det`; TPAMI]
- [PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences](https://arxiv.org/pdf/2205.13713.pdf) [`action recognition`, `seg`; ICLR]
- [PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds](https://arxiv.org/pdf/2103.02766.pdf) [`wireframe`; ICLR]
- [Self-Guided Instance-Aware Network for Depth Completion and Enhancement](https://arxiv.org/pdf/2105.12186.pdf) [`depth`; ICRA]
- [FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection](https://arxiv.org/pdf/2105.07647.pdf) [`det`; [Github](https://github.com/weiyithu/FGR); ICRA]
- [Exploiting Local Geometry for Feature and Graph Construction for Better 3D Point Cloud Processing with Graph Neural Networks](https://arxiv.org/pdf/2103.15226.pdf) [`cls`, `seg`; ICRA]
- [3D3L: Deep Learned 3D Keypoint Detection and Description for LiDARs](https://arxiv.org/pdf/2103.13808.pdf) [`keypoint`; [Github](https://github.com/ethz-asl/3d3l); ICRA]
- [NDT-Transformer: Large-Scale 3D Point Cloud Localisation using the Normal Distribution Transform Representation](https://arxiv.org/pdf/2103.12292.pdf) [`localisation`; ICRA]
- [Volumetric Propagation Network: Stereo-LiDAR Fusion for Long-Range Depth Estimation](https://arxiv.org/pdf/2103.12964.pdf) [`depth estimation`; ICRA]
- [YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection](https://arxiv.org/pdf/2103.09422.pdf) [`det`; [PyTorch](https://github.com/Owen-Liuyuxuan/visualDet3D); ICRA]
- [ERASOR: Egocentric Ratio of Pseudo Occupancy-based Dynamic Object Removal for Static 3D Point Cloud Map Building](https://arxiv.org/pdf/2103.04316.pdf) [`static map`; ICRA]
- [CloudAAE: Learning 6D Object Pose Regression with On-line Data Synthesis on Point Clouds](https://arxiv.org/pdf/2103.01977.pdf) [`pose estimation`; [Tensorflow](https://github.com/GeeeG/CloudAAE); ICRA]
- [Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline](https://arxiv.org/pdf/2106.05304.pdf) [`cls`; [PyTorch](https://github.com/princeton-vl/SimpleView); ICML]
- [PointCutMix: Regularization Strategy for Point Cloud Classification](https://arxiv.org/pdf/2101.01461.pdf) [`cls`; [code](https://github.com/cuge1995/PointCutMix); ICML]
- [Investigate Indistinguishable Points in Semantic Segmentation of 3D Point Cloud](https://arxiv.org/pdf/2103.10339.pdf) [`seg`; [Github](https://github.com/MingyeXu/IAF-Net); AAAI]
- [PointINet: Point Cloud Frame Interpolation Network](https://arxiv.org/pdf/2012.10066.pdf) [`frame interpolation`; [PyTorch](https://github.com/ispc-lab/PointINet); AAAI]
- [Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds](https://arxiv.org/pdf/2101.02381.pdf) [`seg`; [code](https://github.com/JchenXu/BoundaryAwareGEM); AAAI]
- [Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection](https://arxiv.org/pdf/2012.15712.pdf) [`det`; AAAI]
- [Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud](https://arxiv.org/pdf/2012.10921.pdf) [`cls`, `seg`; AAAI]
- [CIA-SSD: Confident IoU-Aware Single-Stage Object Detector From Point Cloud](https://arxiv.org/pdf/2012.03015.pdf) [`det`; [PyTorch](https://github.com/Vegeta2020/CIA-SSD); AAAI]
- [Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion](https://arxiv.org/pdf/2012.03762.pdf) [`seg`; [Github](https://github.com/yanx27/JS3C-Net); AAAI]
- [labelCloud: A Lightweight Domain-Independent Labeling Tool for 3D Object Detection in Point Clouds](https://arxiv.org/pdf/2103.04970.pdf) [`labeling tool`; CAD]
- [CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection](https://openaccess.thecvf.com/content/WACV2021/papers/Nabati_CenterFusion_Center-Based_Radar_and_Camera_Fusion_for_3D_Object_Detection_WACV_2021_paper.pdf) [`det`; [PyTorch](https://github.com/mrnabati/CenterFusion); WACV]
- [Self-Supervised Learning for Domain Adaptation on Point Clouds](https://arxiv.org/pdf/2003.12641v3.pdf) [`cls`, `seg`; WACV]
- arXiv
- [COTReg: Coupled Optimal Transport based Point Cloud Registration](https://arxiv.org/pdf/2112.14381.pdf) [`registration`]
- [iSeg3D: An Interactive 3D Shape Segmentation Tool](https://arxiv.org/pdf/2112.12988.pdf) [`seg`, `annotation tool`]
- [Multi-View Partial (MVP) Point Cloud Challenge 2021 on Completion and Registration: Methods and Results](https://arxiv.org/pdf/2112.12053.pdf) [`completion`, `registration`; [PyTorch](https://github.com/paul007pl/MVP_Benchmark)]
- [BEVDet: High-Performance Multi-Camera 3D Object Detection in Bird-Eye-View](https://arxiv.org/pdf/2112.11790.pdf) [`det`; [Github](https://github.com/HuangJunJie2017/BEVDet)]
- [Revisiting Transformation Invariant Geometric Deep Learning: Are Initial Representations All You Need?](https://arxiv.org/pdf/2112.12345.pdf) [`transformation invariant`]
- [High-Fidelity Point Cloud Completion with Low-Resolution Recovery and Noise-Aware Upsampling](https://arxiv.org/pdf/2112.11271.pdf) [`completion`]
- [EPNet++: Cascade Bi-directional Fusion for Multi-Modal 3D Object Detection](https://arxiv.org/pdf/2112.11088.pdf) [`det`]
- [Domain Adaptation on Point Clouds via Geometry-Aware Implicits](https://arxiv.org/pdf/2112.09343.pdf) [`domain adaptation`]
- [Immortal Tracker: Tracklet Never Dies](https://arxiv.org/pdf/2111.13672.pdf) [`tracking`; [Github](https://github.com/ImmortalTracker/ImmortalTracker)]
- [Semi-supervised Implicit Scene Completion from Sparse LiDAR](https://arxiv.org/pdf/2111.14798.pdf) [`completion`; [PyTorch](https://github.com/OPEN-AIR-SUN/SISC)]
- [GenReg: Deep Generative Method for Fast Point Cloud Registration](https://arxiv.org/pdf/2111.11783.pdf) [`registration`]
- [Deep Point Cloud Reconstruction](https://arxiv.org/pdf/2111.11704.pdf) [`reconstruction`]
- [MFM-Net: Unpaired Shape Completion Network with Multi-stage Feature Matching](https://arxiv.org/pdf/2111.11976.pdf) [`completion`]
- [What Stops Learning-based 3D Registration from Working in the Real World?](https://arxiv.org/pdf/2111.10399.pdf) [`registration`]
- [CpT: Convolutional Point Transformer for 3D Point Cloud Processing](https://arxiv.org/pdf/2111.10866.pdf) [`cls`, `seg`]
- [RAANet: Range-Aware Attention Network for LiDAR-based 3D Object Detection with Auxiliary Density Level Estimation](https://arxiv.org/pdf/2111.09515.pdf) [`det`; [PyTorch](https://github.com/anonymous0522/RAAN)]
- [DRINet++: Efficient Voxel-as-point Point Cloud Segmentation](https://arxiv.org/pdf/2111.08318.pdf) [`seg`]
- [Robust 3D Scene Segmentation through Hierarchical and Learnable Part-Fusion](https://arxiv.org/pdf/2111.08434.pdf) [`seg`]
- [DFC: Deep Feature Consistency for Robust Point Cloud Registration](https://arxiv.org/pdf/2111.07597.pdf) [`registration`]
- [Interpreting Representation Quality of DNNs for 3D Point Cloud Processing](https://arxiv.org/pdf/2111.03549.pdf)
- [CPSeg: Cluster-free Panoptic Segmentation of 3D LiDAR Point Clouds](https://arxiv.org/pdf/2111.01723.pdf) [`seg`]
- [Structure Information is the Key: Self-Attention RoI Feature Extractor in 3D Object Detection](https://arxiv.org/pdf/2111.00931.pdf) [`det`; [Github](https://github.com/Poley97/SARFE)]
- [Deep Models with Fusion Strategies for MVP Point Cloud Registration](https://arxiv.org/pdf/2110.09129.pdf) [`registration`]
- [Improved Pillar with Fine-grained Feature for 3D Object Detection](https://arxiv.org/pdf/2110.06049.pdf) [`det`]
- [3D Object Detection Combining Semantic and Geometric Features from Point Clouds](https://arxiv.org/pdf/2110.04704.pdf) [`det`]
- [How to Build a Curb Dataset with LiDAR Data for Autonomous Driving](https://arxiv.org/pdf/2110.03968.pdf) [`autonomous driving`]
- [3D-FCT: Simultaneous 3D Object Detection and Tracking Using Feature Correlation](https://arxiv.org/pdf/2110.02531.pdf) [`det`, `tracking`]
- [GP-S3Net: Graph-based Panoptic Sparse Semantic Segmentation Network](https://arxiv.org/pdf/2108.08401.pdf) [`seg`]
- [SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation](https://arxiv.org/pdf/2108.06709.pdf) [`det`]
- [Progressive Coordinate Transforms for Monocular 3D Object Detection](https://arxiv.org/pdf/2108.05793.pdf) [`monocular`, `det`; [Github](https://github.com/amazon-research/progressive-coordinate-transforms)]
- [Real-Time Anchor-Free Single-Stage 3D Detection with IoU-Awareness](https://arxiv.org/pdf/2107.14342.pdf) [`det`]
- [Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection](https://arxiv.org/pdf/2107.13931.pdf) [`det`; [Github](https://github.com/YinminZhang/MonoGeo)]
- [CarveNet: Carving Point-Block for Complex 3D Shape Completion](https://arxiv.org/pdf/2107.13452.pdf) [`completion`]
- [CKConv: Learning Feature Voxelization for Point Cloud Analysis](https://arxiv.org/pdf/2107.12655.pdf) [`cls`, `seg`]
- [DV-Det: Efficient 3D Point Cloud Object Detection with Dynamic Voxelization](https://arxiv.org/pdf/2107.12707.pdf) [`det`]
- [Unsupervised Domain Adaptation in LiDAR Semantic Segmentation with Self-Supervision and Gated Adapters](https://arxiv.org/pdf/2107.09783.pdf) [`seg`]
- [Dynamic Convolution for 3D Point Cloud Instance Segmentation](https://arxiv.org/pdf/2107.08392.pdf)[`seg`; [PyTorch](https://github.com/aim-uofa/DyCo3D)]
- [Beyond Farthest Point Sampling in Point-Wise Analysis](https://arxiv.org/pdf/2107.04291.pdf) [`sampling`]
- [Learn to Learn Metric Space for Few-Shot Segmentation of 3D Shapes](https://arxiv.org/pdf/2107.02972.pdf) [`seg`]
- [Multi-Modality Task Cascade for 3D Object Detection](https://arxiv.org/pdf/2107.04013.pdf) [`det`; [Github](https://github.com/Divadi/MTC_RCNN)]
- [Point Cloud Registration using Representative Overlapping Points](https://arxiv.org/pdf/2107.02583.pdf) [`registration`; [PyTorch](https://github.com/zhulf0804/ROPNet)]
- [“Zero Shot” Point Cloud Upsampling](https://arxiv.org/pdf/2106.13765.pdf) [`upsampling`]
- [3D Shape Registration Using Spectral Graph Embedding and Probabilistic Matching](https://arxiv.org/pdf/2106.11166.pdf) [`registration`]
- [Z2P: Instant Rendering of Point Clouds](https://arxiv.org/pdf/2105.14548.pdf) [`rendering`]
- [TransLoc3D : Point Cloud based Large-scale Place Recognition using Adaptive Receptive Fields](https://arxiv.org/pdf/2105.11605.pdf) [`place recognition`]
- [Generalisable and distinctive 3D local deep descriptors for point cloud registration](https://arxiv.org/pdf/2105.10382.pdf) [`registration`]
- [Deep Weighted Consensus (DWC) Dense correspondence confidence maps for 3D shape registration](https://arxiv.org/pdf/2105.02714.pdf) [`registration`]
- [Boundary-Aware 3D Object Detection from Point Clouds](https://arxiv.org/pdf/2104.10330.pdf) [`det`]
- [Geometry-aware data augmentation for monocular 3D object detection](https://arxiv.org/pdf/2104.05858.pdf) [`det`]
- [OCM3D: Object-Centric Monocular 3D Object Detection](https://arxiv.org/pdf/2104.06041.pdf) [`det`]
- [Towards Efficient Graph Convolutional Networks for Point Cloud Handling](https://arxiv.org/pdf/2104.05706.pdf) [`network`; [Github](https://github.com/ofsoundof/EfficientGCN)]
- [Occlusion Guided Self-supervised Scene Flow Estimation on 3D Point Clouds](https://arxiv.org/pdf/2104.04724.pdf) [`scene flow`]
- [A Learnable Self-supervised Task for Unsupervised Domain Adaptation on Point Clouds](https://arxiv.org/pdf/2104.05164.pdf) [`UDA`]
- [View-Guided Point Cloud Completion](https://arxiv.org/pdf/2104.05666.pdf) [`completion`]
- [One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation](https://arxiv.org/pdf/2104.02246.pdf) [`seg`]
- [Potential Convolution: Embedding Point Clouds into Potential Fields](https://arxiv.org/pdf/2104.01754.pdf) [`cls`, `seg`]
- [3D-MAN: 3D Multi-frame Attention Network for Object Detection](https://arxiv.org/pdf/2103.16054.pdf) [`det`]
- [X-view: Non-egocentric Multi-View 3D Object Detector](https://arxiv.org/pdf/2103.13001.pdf) [`det`]
- [RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation](https://arxiv.org/pdf/2103.12978.pdf) [`seg`]
- [SparsePoint: Fully End-to-End Sparse 3D Object Detector](https://arxiv.org/pdf/2103.10042.pdf) [`det`]
- [S3Net: 3D LiDAR Sparse Semantic Segmentation Network](https://arxiv.org/pdf/2103.08745.pdf) [`seg`]
- [Lite-HDSeg: LiDAR Semantic Segmentation Using Lite Harmonic Dense Convolutions](https://arxiv.org/pdf/2103.08852.pdf) [`seg`]
- [MapFusion: A General Framework for 3D Object Detection with HDMaps](https://arxiv.org/pdf/2103.05929.pdf) [`det`]
- [Offboard 3D Object Detection from Point Cloud Sequences](https://arxiv.org/pdf/2103.05073.pdf) [`det`]
- [A Simple and Efficient Multi-task Network for 3D Object Detection and Road Understanding](https://arxiv.org/pdf/2103.04056.pdf) [`det`; [PyTorch](https://github.com/frankfengdi/LidarMTL)]
- [IRON: Invariant-based Highly Robust Point Cloud Registration](https://arxiv.org/pdf/2103.04357.pdf) [`registration`]
- [EllipsoidNet: Ellipsoid Representation for Point Cloud Classification and Segmentation](https://arxiv.org/pdf/2103.02517.pdf) [`cls`, `seg`]
- [Pseudo-labeling for Scalable 3D Object Detection](https://arxiv.org/pdf/2103.02093.pdf) [`det`]
- [LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignment](https://arxiv.org/pdf/2103.02263.pdf) [`seg`]
- [Scalable Scene Flow from Point Clouds in the Real World](https://arxiv.org/pdf/2103.01306.pdf) [`scene flow`]
- [InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring](https://arxiv.org/pdf/2103.01128.pdf) [`visual grounding`]
- [FPS-Net: A Convolutional Fusion Network
for Large-Scale LiDAR Point Cloud Segmentation](https://arxiv.org/pdf/2103.00738.pdf) [`seg`]
- [Attention Models for Point Clouds in Deep Learning: A Survey](https://arxiv.org/pdf/2102.10788.pdf) [`attention`]
- [EfficientLPS: Efficient LiDAR Panoptic
Segmentation](https://arxiv.org/pdf/2102.08009.pdf) [`seg`]
- [HyperPocket: Generative Point Cloud Completion](https://arxiv.org/pdf/2102.05973.pdf) [`completion`]
- [Point-set Distances for Learning Representations of 3D Point Clouds](https://arxiv.org/pdf/2102.04014.pdf) [`representation`]
- [DPointNet: A Density-Oriented PointNet for 3D Object Detection in Point Clouds](https://arxiv.org/pdf/2102.03747.pdf) [`det`]
- [PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection](https://arxiv.org/pdf/2102.00463.pdf) [`det`; [OpenPCDet](https://github.com/open-mmlab/OpenPCDet)]
- [Self-Attention Based Context-Aware 3D Object Detection](https://arxiv.org/pdf/2101.02672.pdf) [`det`; [PyTorch](https://github.com/AutoVision-cloud/SA-Det3D)]
- [A two-stage data association approach for 3D Multi-object Tracking](https://arxiv.org/pdf/2101.08684.pdf) [`tracking`]
- [The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions](https://arxiv.org/pdf/2101.07832.pdf) [`seg`]
## 2020
- ECCV
- [Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots](https://arxiv.org/pdf/1912.12791.pdf?ref=https://githubhelp.com) [`det`]
- [PointMixup: Augmentation for point cloud](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123480341.pdf) [`augmentation`, `cls`; [PyTorch](https://github.com/yunlu-chen/PointMixup)]
- [Deformable PV-RCNN: Improving 3D Object Detection with Learned Deformations](https://arxiv.org/pdf/2008.08766.pdf) [`det`; [PyTorch](https://github.com/AutoVision-cloud/Deformable-PV-RCNN)]
- [Unsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Sets](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123700545.pdf) [`keypoints`]
- [Weakly-supervised 3D Shape Completion in the Wild](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123500273.pdf) [`completion`]
- [SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123480069.pdf) [`completion`, `cls`; [Github](https://github.com/wangyida/softpool)]
- [Detail Preserved Point Cloud Completion via Separated Feature Aggregation](https://arxiv.org/pdf/2007.02374.pdf) [`completion`; [Tensorflow](https://github.com/XLechter/Detail-Preserved-Point-Cloud-Completion-via-SFA)]
- [PointPWC-Net: A Coarse-to-Fine Network for Supervised and Self-Supervised Scene Flow Estimation on 3D Point Clouds](https://arxiv.org/pdf/1911.12408.pdf) [`flow estimation`; [PyTorch](https://github.com/DylanWusee/PointPWC)]
- [JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds](https://arxiv.org/pdf/2007.06888.pdf) [`seg`; [Tensorflow](https://github.com/hzykent/JSENet)]
- [A Closer Look at Local Aggregation Operators in Point Cloud Analysis](https://arxiv.org/pdf/2007.01294.pdf) [`cls`, `seg`; [Code](https://github.com/zeliu98/CloserLook3D)]
- [Instance-Aware Embedding for Point Cloud Instance Segmentation](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123750256.pdf) [`seg`]
- [Multimodal Shape Completion via Conditional Generative Adversarial Networks](https://arxiv.org/pdf/2003.07717.pdf) [`completion`; [PyTorch](https://github.com/ChrisWu1997/Multimodal-Shape-Completion)]
- [GRNet: Gridding Residual Network for Dense Point Cloud Completion](https://arxiv.org/pdf/2006.03761.pdf) [`completion`; [PyTorch](https://github.com/hzxie/GRNet)]
- [3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection](https://arxiv.org/pdf/2004.12636.pdf) [`det`]
- [SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds](https://arxiv.org/pdf/2004.02774.pdf) [`det`; [Github](https://github.com/xinge008/SSN)]
- [Pillar-based Object Detection for Autonomous Driving](https://arxiv.org/pdf/2007.10323.pdf) [`det`, `autonomous driving`; [Tensorflow](https://github.com/WangYueFt/pillar-od)]
- [EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection](https://arxiv.org/pdf/2007.08856.pdf) [`det`; [PyTorch](https://github.com/happinesslz/EPNet)]
- [Finding Your (3D) Center: 3D Object Detection Using a Learned Loss](https://arxiv.org/pdf/2004.02693.pdf) [`det`; [Tensorflow](https://github.com/dgriffiths3/finding-your-center)]
- [Weakly Supervised 3D Object Detection from Lidar Point Cloud](https://arxiv.org/pdf/2007.11901.pdf) [`det`; [PyTorch](https://github.com/hlesmqh/WS3D)]
- [H3DNet: 3D Object Detection Using Hybrid Geometric Primitives](https://arxiv.org/pdf/2006.05682.pdf) [`det`; [Tensorflow](https://github.com/zaiweizhang/H3DNet)]
- [Generative Sparse Detection Networks for 3D Single-shot Object Detection](https://arxiv.org/pdf/2006.12356.pdf) [`det`; [Github](https://github.com/jgwak/GSDN)]
- [Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution](https://arxiv.org/pdf/2007.16100.pdf) [`seg`, `det`; [PyTorch](https://github.com/mit-han-lab/e3d)]
- [DeepGMR: Learning Latent Gaussian Mixture Models for Registration](https://arxiv.org/pdf/2008.09088.pdf) [`registration`; [PyTorch](https://github.com/wentaoyuan/deepgmr)]
- [Quaternion Equivariant Capsule Networks for 3D Point Clouds](https://arxiv.org/pdf/1912.12098.pdf) [[PyTorch](https://github.com/tolgabirdal/qecnetworks)]
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://arxiv.org/pdf/2007.10985.pdf) [`unsupervised`; `cls`, `seg`, `det`; [PyTorch](https://github.com/facebookresearch/PointContrast)]
- [Convolutional Occupancy Networks](https://arxiv.org/pdf/2003.04618.pdf) [`reconstruction`; [PyTorch](https://github.com/autonomousvision/convolutional_occupancy_networks)]
- [Iterative Distance-Aware Similarity Matrix Convolution with Mutual-Supervised Point Elimination for Efficient Point Cloud Registration](https://arxiv.org/pdf/1910.10328.pdf) [`registration`; [PyTorch](https://github.com/jiahaowork/idam)]
- [Progressive Point Cloud Deconvolution Generation Network](https://arxiv.org/pdf/2007.05361.pdf) [`generation`; [github](https://github.com/fpthink/PDGN)]
- [Reinforced Axial Refinement Network for Monocular 3D Object Detection](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123620528.pdf) [`det`, `monocular`]
- [Monocular 3D Object Detection via Feature Domain Adaptation](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123540018.pdf) [`det`, `monocular`]
- [Improving 3D Object Detection through Progressive Population Based Augmentation](https://arxiv.org/pdf/2004.00831.pdf) [`det`]
- [An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds](https://arxiv.org/pdf/2007.12392.pdf) [`det`]
- [Rotation-robust Intersection over Union for 3D Object Detection](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123650460.pdf)
- [DPDist: Comparing Point Clouds Using Deep Point Cloud Distance](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123560528.pdf)
- CVPR
- [End-to-end pseudo-lidar for image-based 3d object detection](https://openaccess.thecvf.com/content_CVPR_2020/papers/Qian_End-to-End_Pseudo-LiDAR_for_Image-Based_3D_Object_Detection_CVPR_2020_paper.pdf) [`det`; [PyTorch](https://github.com/mileyan/pseudo-LiDAR_e2e)]
- [PointPainting: Sequential Fusion for 3D Object Detection](https://openaccess.thecvf.com/content_CVPR_2020/papers/Vora_PointPainting_Sequential_Fusion_for_3D_Object_Detection_CVPR_2020_paper.pdf) [`det`]
- [3DSSD: Point-based 3D Single Stage Object Detector](https://openaccess.thecvf.com/content_CVPR_2020/papers/Yang_3DSSD_Point-Based_3D_Single_Stage_Object_Detector_CVPR_2020_paper.pdf) [`det`; [Tensorflow](https://github.com/Jia-Research-Lab/3DSSD)]
- [A Hierarchical Graph Network for 3D Object Detection on Point Clouds](https://openaccess.thecvf.com/content_CVPR_2020/papers/Chen_A_Hierarchical_Graph_Network_for_3D_Object_Detection_on_Point_CVPR_2020_paper.pdf) [`det`]
- [Deep Geometric Functional Maps: Robust Feature Learning for Shape Correspondence](https://openaccess.thecvf.com/content_CVPR_2020/papers/Donati_Deep_Geometric_Functional_Maps_Robust_Feature_Learning_for_Shape_Correspondence_CVPR_2020_paper.pdf) [`correspondences`; [Tensorflow](https://github.com/LIX-shape-analysis/GeomFmaps)]
- [Deep Global Registration](https://arxiv.org/pdf/2004.11540.pdf) [`registration`; [PyTorch](https://github.com/chrischoy/DeepGlobalRegistration)]
- [3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation](https://arxiv.org/pdf/2003.13867.pdf) [`seg`; [Github](https://github.com/francisengelmann/3D-MPA)]
- [PointGMM: a Neural GMM Network for Point Clouds](https://openaccess.thecvf.com/content_CVPR_2020/papers/Hertz_PointGMM_A_Neural_GMM_Network_for_Point_Clouds_CVPR_2020_paper.pdf) [`generation`, `registration`; [PyTorch](https://github.com/amirhertz/pointgmm)]
- [Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud](https://openaccess.thecvf.com/content_CVPR_2020/papers/Shi_Point-GNN_Graph_Neural_Network_for_3D_Object_Detection_in_a_CVPR_2020_paper.pdf) [`det`; [Tensorflow](https://github.com/WeijingShi/Point-GNN)]
- [ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votes](https://openaccess.thecvf.com/content_CVPR_2020/papers/Qi_ImVoteNet_Boosting_3D_Object_Detection_in_Point_Clouds_With_Image_CVPR_2020_paper.pdf) [`det`]
- [OccuSeg: Occupancy-aware 3D Instance Segmentation](https://openaccess.thecvf.com/content_CVPR_2020/papers/Han_OccuSeg_Occupancy-Aware_3D_Instance_Segmentation_CVPR_2020_paper.pdf) [`seg`]
- [Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation](https://arxiv.org/pdf/2003.06233.pdf) [`seg`; [PyTorch](https://github.com/jzhzhang/FusionAwareConv)]
- [MLCVNet: Multi-Level Context VoteNet for 3D Object Detection](https://openaccess.thecvf.com/content_CVPR_2020/papers/Xie_MLCVNet_Multi-Level_Context_VoteNet_for_3D_Object_Detection_CVPR_2020_paper.pdf) [`det`; [PyTorch](https://github.com/NUAAXQ/MLCVNet)]
- [Going Deeper with Lean Point Networks](https://openaccess.thecvf.com/content_CVPR_2020/papers/Le_Going_Deeper_With_Lean_Point_Networks_CVPR_2020_paper.pdf) [`seg`; [PyTorch](https://github.com/erictuanle/GoingDeeperwPointNetworks)]
- [Point Cloud Completion by Skip-attention Network with Hierarchical Folding](https://arxiv.org/pdf/2005.03871.pdf) [`completion`]
- [Unsupervised Learning of Intrinsic Structural Representation Points](https://arxiv.org/pdf/2003.01661.pdf) [[PyTorch](https://github.com/NolenChen/3DStructurePoints)]
- [PF-Net: Point Fractal Network for 3D Point Cloud Completion](https://openaccess.thecvf.com/content_CVPR_2020/papers/Huang_PF-Net_Point_Fractal_Network_for_3D_Point_Cloud_Completion_CVPR_2020_paper.pdf) [`completion`; [PyTorch](https://github.com/zztianzz/PF-Net-Point-Fractal-Network)]
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://openaccess.thecvf.com/content_CVPR_2020/papers/Shi_PV-RCNN_Point-Voxel_Feature_Set_Abstraction_for_3D_Object_Detection_CVPR_2020_paper.pdf) [`det`; [code](https://github.com/open-mmlab/OpenPCDet)]
- [Adaptive Hierarchical Down-Sampling for Point Cloud Classification](https://openaccess.thecvf.com/content_CVPR_2020/papers/Nezhadarya_Adaptive_Hierarchical_Down-Sampling_for_Point_Cloud_Classification_CVPR_2020_paper.pdf) [`downsampling`, `cls`]
- [SA-SSD: Structure Aware Single-stage 3D Object Detection from Point Cloud](https://www4.comp.polyu.edu.hk/~cslzhang/paper/SA-SSD.pdf) [`det`; [PyTorch](https://github.com/skyhehe123/SA-SSD)]
- [3DRegNet: A Deep Neural Network for 3D Point Registration](https://openaccess.thecvf.com/content_CVPR_2020/papers/Pais_3DRegNet_A_Deep_Neural_Network_for_3D_Point_Registration_CVPR_2020_paper.pdf) [`registration`; [Tensorflow](https://github.com/3DVisionISR/3DRegNet)]
- [MINA: Convex Mixed-Integer Programming for Non-Rigid Shape Alignment](https://openaccess.thecvf.com/content_CVPR_2020/papers/Bernard_MINA_Convex_Mixed-Integer_Programming_for_Non-Rigid_Shape_Alignment_CVPR_2020_paper.pdf) [`non-rigid alignment`]
- [SampleNet: Differentiable Point Cloud Sampling](https://openaccess.thecvf.com/content_CVPR_2020/papers/Lang_SampleNet_Differentiable_Point_Cloud_Sampling_CVPR_2020_paper.pdf) [`sample`, `cls`, `registration`, `reconstruction`; [PyTorch](https://github.com/itailang/SampleNet)]
- [Learning multiview 3D point cloud registration](https://arxiv.org/pdf/2001.05119.pdf) [`multiview registration`; [PyTorch](https://github.com/zgojcic/3D_multiview_reg)]
- [Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondences](https://arxiv.org/pdf/2005.01014.pdf) [`registration`; [PyTorch](https://github.com/XiaoshuiHuang/fmr)]
- [PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling](https://arxiv.org/pdf/2003.00492.pdf) [`cls`, `seg`; [Tensorflow](https://github.com/yanx27/PointASNL)]
- [Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds](https://arxiv.org/pdf/2003.12971.pdf) [`unsupervised`; `cls`; [PyTorch](https://github.com/raoyongming/PointGLR)]
- [Grid-GCN for Fast and Scalable Point Cloud Learning](https://arxiv.org/pdf/1912.02984.pdf) [`cls`, `seg`; [mxnet](https://github.com/Xharlie/Grid-GCN)]
- [FPConv: Learning Local Flattening for Point Convolution](https://arxiv.org/pdf/2002.10701.pdf) [`cls`, `seg`; [PyTorch](https://github.com/lyqun/FPConv)]
- [PointAugment: an Auto-Augmentation Framework for Point Cloud Classification](https://arxiv.org/pdf/2002.10876.pdf) [`cls`, `retrieval`; [github](https://github.com/liruihui/PointAugment/)]
- [RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds](https://arxiv.org/pdf/1911.11236.pdf) [`seg`; [Tensorflow](https://github.com/QingyongHu/RandLA-Net)]
- [Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labels](https://arxiv.org/pdf/2004.04091.pdf) [`weakly supervised`; `seg`; [Tensorflow](https://github.com/alex-xun-xu/WeakSupPointCloudSeg)]
- [PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation](https://arxiv.org/pdf/2003.14032.pdf) [`seg`; [PyTorch](https://github.com/edwardzhou130/PolarSeg)]
- [Learning to Segment 3D Point Clouds in 2D Image Space](https://arxiv.org/pdf/2003.05593.pdf) [`seg`; [Keras](https://github.com/Zhang-VISLab/Learning-to-Segment-3D-Point-Clouds-in-2D-Image-Space)]
- [PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation](https://arxiv.org/pdf/2004.01658.pdf) [`seg`; [PyTorch](https://github.com/Jia-Research-Lab/PointGroup)]
- [D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features](https://arxiv.org/pdf/2003.03164.pdf) [`keypoints`, `registration`; [Tensorflow](https://github.com/XuyangBai/D3Feat), [PyTorch](https://github.com/XuyangBai/D3Feat.pytorch)]
- [RPM-Net: Robust Point Matching using Learned Features](https://arxiv.org/pdf/2003.13479.pdf) [`registration`; [PyTorch](https://github.com/yewzijian/RPMNet)]
- [Cascaded Refinement Network for Point Cloud Completion](https://arxiv.org/pdf/2004.03327.pdf) [`completion`; [Tensorflow](https://github.com/xiaogangw/cascaded-point-completion)]
- [P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds](https://arxiv.org/pdf/2005.13888.pdf) [`tracking`; [PyTorch](https://github.com/HaozheQi/P2B)]
- [An Efficient PointLSTM for Point Clouds Based Gesture Recognition](https://openaccess.thecvf.com/content_CVPR_2020/papers/Min_An_Efficient_PointLSTM_for_Point_Clouds_Based_Gesture_Recognition_CVPR_2020_paper.pdf) [`gesture`; [PyTorch](https://github.com/Blueprintf/pointlstm-gesture-recognition-pytorch)]
- Others
- [Group Contextual Encoding for 3D Point Clouds](https://papers.nips.cc/paper/2020/file/9b72e31dac81715466cd580a448cf823-Paper.pdf) [`det`, `cls`; [PyTorch](https://github.com/AsahiLiu/PointDetectron); NeurIPS]
- [CaSPR: Learning Canonical Spatiotemporal
Point Cloud Representations](https://arxiv.org/pdf/2008.02792.pdf) [`dynamic sequences`; [Github](https://github.com/davrempe/caspr); NeurIPS]
- [Skeleton-bridged Point Completion: From Global Inference to Local Adjustment](https://papers.nips.cc/paper/2020/file/ba036d228858d76fb89189853a5503bd-Paper.pdf) [`completion`; NeurIPS]
- [Self-Supervised Few-Shot Learning on Point Clouds](https://arxiv.org/pdf/2009.14168.pdf) [`cls`, `seg`; NeurIPS]
- [Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloud](https://arxiv.org/pdf/2010.03318.pdf) [`cls`; NeurIPS]
- [PIE-NET: Parametric Inference of Point Cloud Edges](https://arxiv.org/pdf/2007.04883.pdf) [`edge det`; NeurIPS]
- [Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds](https://arxiv.org/pdf/1909.09287.pdf) [`cls`, `seg`; [Tensorflow](https://github.com/hlei-ziyan/SPH3D-GCN); TPAMI]
- [From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network](https://arxiv.org/pdf/1907.03670.pdf) [`det`; [PyTorch](https://github.com/open-mmlab/OpenPCDet); TPAMI]
- [Unpaired Point Cloud Completion on Real Scans using Adversarial Training](https://arxiv.org/pdf/1904.00069.pdf) [`completion`; [Tensorflow](https://github.com/xuelin-chen/pcl2pcl-gan-pub); ICLR]
- [AdvectiveNet: An Eulerian-Lagrangian Fluidic Reservoir for Point Cloud Processing](https://arxiv.org/pdf/2002.00118.pdf) [`cls`, `seg`; [PyTorch](https://github.com/xingzhehe/AdvectiveNet-An-Eulerian-Lagrangian-Fluidic-Reservoir-for-Point-Cloud-Processing); ICLR]
- [Tranquil Clouds: Neural Networks for Learning Temporally Coherent Features in Point Clouds](https://arxiv.org/pdf/1907.05279.pdf) [ICLR]
- [PI-RCNN: An Efficient Multi-Sensor 3D Object Detector with Point-Based Attentive Cont-Conv Fusion Module](https://ojs.aaai.org/index.php/AAAI/article/view/6933/6787) [`det`; AAAI]
- [MSN: Morphing and Sampling Network for Dense Point Cloud Completion](https://cseweb.ucsd.edu/~mil070/projects/AAAI2020/paper.pdf) [`completion`; [PyTorch](https://github.com/Colin97/MSN-Point-Cloud-Completion); AAAI]
- [TANet: Robust 3D Object Detection from Point Clouds with Triple Attention](https://arxiv.org/pdf/1912.05163.pdf) [`det`; [PyTorch](https://github.com/happinesslz/TANet); AAAI]
- [JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds](https://arxiv.org/pdf/1912.09654.pdf) [`seg`; [Tensorflow](https://github.com/dlinzhao/JSNet)]
- [Point2Node: Correlation Learning of Dynamic-Node for Point Cloud Feature Modeling](https://arxiv.org/pdf/1912.10775.pdf) [`cls`, `seg`; AAAI]
- [Pointwise Rotation-Invariant Network with Adaptive Sampling and 3D Spherical Voxel Convolution](https://arxiv.org/pdf/1811.09361.pdf) [`cls`, `seg`, `matching`; AAAI]
- [Differentiable Manifold Reconstruction for Point Cloud Denoising](https://arxiv.org/pdf/2007.13551.pdf) [`denoising`; [PyTorch](https://github.com/luost26/DMRDenoise); ACM MM]
- [Weakly Supervised 3D Object Detection from Point Clouds](https://arxiv.org/pdf/2007.13970.pdf) [`det`; [Tensorflow](https://github.com/Zengyi-Qin/Weakly-Supervised-3D-Object-Detection); ACM MM]
- [TEASER: Fast and Certifiable Point Cloud Registration](https://arxiv.org/pdf/2001.07715.pdf) [`registration`; [Github](https://github.com/MIT-SPARK/TEASER-plusplus); TRO]
- [Unsupervised Detection of Distinctive Regions on 3D Shapes](https://arxiv.org/pdf/1905.01684.pdf) [`unsupervised`; [Tensorflow](https://github.com/nini-lxz/Unsupervised-Shape-Distinction-Detection); TOG]
- [SegVoxelNet: Exploring Semantic Context and Depth-aware Features for 3D Vehicle Detection from Point Cloud](https://arxiv.org/pdf/2002.05316.pdf) [`det`; ICRA]
- [Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds](https://arxiv.org/pdf/1907.12046.pdf) [`seg`, `cls`; [Project](https://francisengelmann.github.io/DPC/); ICRA]
- [Semantic Graph Based Place Recognition for 3D Point Clouds](https://ras.papercept.net/proceedings/IROS20/0170.pdf) [`place recognition`; [PyTorch](https://github.com/kxhit/SG_PR); IROS]
- [End-to-End 3D Point Cloud Learning for Registration Task Using Virtual Correspondences](https://ras.papercept.net/proceedings/IROS20/1105.pdf) [`registration`; [PyTorch](https://github.com/qiaozhijian/VCR-Net); IROS]
- [Correspondence Matrices are Underrated](https://arxiv.org/pdf/2010.16085.pdf) [`registration, correspondence`; [PyTorch](https://github.com/tzodge/PCR-CMU); 3DV]
- [Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networks](https://arxiv.org/abs/2101.00483) [`cls`, `seg`; 3DV]
- [PanoNet3D: Combining Semantic and Geometric Understanding for LiDAR Point Cloud Detection](https://arxiv.org/pdf/2012.09418.pdf) [`det`; 3DV]
- [FKAConv: Feature-Kernel Alignment for Point Cloud Convolution](https://openaccess.thecvf.com/content/ACCV2020/papers/Boulch_FKAConv_Feature-Kernel_Alignment_for_Point_Cloud_Convolution_ACCV_2020_paper.pdf) [`conv`, `cls`, `seg`; [PyTorch](https://github.com/valeoai/LightConvPoint); ACCV]
- [Sparse Convolutions on Continuous Domains for Point Cloud and Event Stream Networks](https://openaccess.thecvf.com/content/ACCV2020/papers/Jack_Sparse_Convolutions_on_Continuous_Domains_for_Point_Cloud_and_Event_ACCV_2020_paper.pdf) [`conv`, `cls`; ACCV]
- [Reconstructing Human Body Mesh from Point Clouds by Adversarial GP Network](https://openaccess.thecvf.com/content/ACCV2020/papers/Zhou_Reconstructing_Human_Body_Mesh_from_Point_Clouds_by_Adversarial_GP_ACCV_2020_paper.pdf) [`reconstruction`; ACCV]
- [Bi-Directional Attention for Joint Instance and Semantic Segmentation in Point Clouds](https://openaccess.thecvf.com/content/ACCV2020/papers/Wu_Bi-Directional_Attention_for_Joint_Instance_and_Semantic_Segmentation_in_Point_ACCV_2020_paper.pdf) [`seg`; [Tensorflow](https://github.com/pumpkinnan/BAN); ACCV]
- [SDP-Net: Scene Flow Based Real-time Object Detection and Prediction from Sequential 3D Point Clouds](https://openaccess.thecvf.com/content/ACCV2020/papers/Zhang_SDP-Net_Scene_Flow_Based_Real-time_Object_Detection_and_Prediction_from_ACCV_2020_paper.pdf) [`det`; ACCV]
- [Best Buddies Registration for Point Clouds](https://openaccess.thecvf.com/content/ACCV2020/papers/Drory_Best_Buddies_Registration_for_Point_Clouds_ACCV_2020_paper.pdf) [`registration`; [PyTorch](https://github.com/AmnonDrory/BestBuddiesRegistration); ACCV]
- [HPGCNN: Hierarchical Parallel Group Convolutional Neural Networks for Point Clouds Processing](https://openaccess.thecvf.com/content/ACCV2020/papers/Dang_HPGCNN_Hierarchical_Parallel_Group_Convolutional_Neural_Networks_for_Point_Clouds_ACCV_2020_paper.pdf) [`conv`, `cls`, `seg`; ACCV]
- [SAUM: Symmetry-Aware Upsampling Module for Consistent Point Cloud Completion](https://openaccess.thecvf.com/content/ACCV2020/papers/Son_SAUM_Symmetry-Aware_Upsampling_Module_for_Consistent_Point_Cloud_Completion_ACCV_2020_paper.pdf) [`completion`; [Tensorflow](https://github.com/countywest/SAUM); ACCV]
- [Fast and Automatic Registration of Terrestrial Point Clouds Using 2D Line Features](https://www.researchgate.net/publication/340771096_Fast_and_Automatic_Registration_of_Terrestrial_Point_Clouds_Using_2D_Line_Features/fulltext/5ea05e5545851564fc34cb0c/Fast-and-Automatic-Registration-of-Terrestrial-Point-Clouds-Using-2D-Line-Features.pdf) [`registration`; Remote Sensing]
- [ConvPoint: Continuous Convolutions for Point Cloud Processing](https://arxiv.org/pdf/1904.02375.pdf) [`cls`, `seg`; [PyTorch](https://github.com/aboulch/ConvPoint); Computers & Graphics]
- arXiv
- [Multi-Modality Cut and Paste for 3D Object Detection](https://arxiv.org/pdf/2012.12741.pdf) [`det`; [PyTorch](https://github.com/open-mmlab/mmdetection3d)]
- [SALA: Soft Assignment Local Aggregation for 3D Semantic Segmentation](https://arxiv.org/pdf/2012.14929.pdf) [`seg`]
- [Compositional Prototype Network with Multi-view Comparision for Few-Shot Point Cloud Semantic Segmentation](https://arxiv.org/pdf/2012.14255.pdf) [`seg`]
- [Geometric robust descriptor for 3D point cloud](https://arxiv.org/pdf/2012.12215.pdf) [`registration`, `cls`, `seg`]
- [Point Transformer(Nico)](https://arxiv.org/pdf/2011.00931.pdf) [`cls`, `seg`]
- [Deterministic PointNetLK for Generalized Registration](https://arxiv.org/pdf/2008.09527.pdf) [`registration`]
- [Learning 3D-3D Correspondences for One-shot Partial-to-partial Registration](https://arxiv.org/pdf/2006.04523.pdf) [`registration`]
- [Continuous Geodesic Convolutions for Learning on 3D Shapes](https://arxiv.org/pdf/2002.02506.pdf) [`descriptor`, `match`, `seg`]
- [Multi-Resolution Graph Neural Network for Large-Scale Pointcloud Segmentation](https://arxiv.org/pdf/2009.08924.pdf) [`seg`]
- [A Density-Aware PointRCNN for 3D Objection Detection in Point Clouds](https://arxiv.org/pdf/2009.05307.pdf) [`det`]
## 2019
- ICCV
- [M3D-RPN: Monocular 3D Region Proposal Network for Object Detection](https://openaccess.thecvf.com/content_ICCV_2019/papers/Brazil_M3D-RPN_Monocular_3D_Region_Proposal_Network_for_Object_Detection_ICCV_2019_paper.pdf) [`det`]
- [Disentangling Monocular 3D Object Detection](https://openaccess.thecvf.com/content_ICCV_2019/papers/Simonelli_Disentangling_Monocular_3D_Object_Detection_ICCV_2019_paper.pdf) [`det`, `monocular`]
- [Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaning](https://openaccess.thecvf.com/content_ICCV_2019/papers/Hermosilla_Total_Denoising_Unsupervised_Learning_of_3D_Point_Cloud_Cleaning_ICCV_2019_paper.pdf) [`denoising`; [Tensorflow](https://github.com/phermosilla/TotalDenoising)]
- [3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions](https://openaccess.thecvf.com/content_ICCV_2019/papers/Shu_3D_Point_Cloud_Generative_Adversarial_Network_Based_on_Tree_Structured_ICCV_2019_paper.pdf) [`generation`; [PyTorch](https://github.com/seowok/TreeGAN)]
- [STD: Sparse-to-Dense 3D Object Detector for Point Cloud](https://openaccess.thecvf.com/content_ICCV_2019/papers/Yang_STD_Sparse-to-Dense_3D_Object_Detector_for_Point_Cloud_ICCV_2019_paper.pdf) [`det`]
- [USIP: Unsupervised Stable Interest Point Detection from 3D Point Clouds](https://openaccess.thecvf.com/content_ICCV_2019/papers/Li_USIP_Unsupervised_Stable_Interest_Point_Detection_From_3D_Point_Clouds_ICCV_2019_paper.pdf) [`keypoints`, `registration`; [PyTorch](https://github.com/lijx10/USIP)]
- [LPD-Net: 3D Point Cloud Learning for Large-Scale Place Recognition and
Environment Analysis](https://openaccess.thecvf.com/content_ICCV_2019/papers/Liu_LPD-Net_3D_Point_Cloud_Learning_for_Large-Scale_Place_Recognition_and_ICCV_2019_paper.pdf) [`place recognition`]
- [Unsupervised Multi-Task Feature Learning on Point Clouds](https://openaccess.thecvf.com/content_ICCV_2019/papers/Hassani_Unsupervised_Multi-Task_Feature_Learning_on_Point_Clouds_ICCV_2019_paper.pdf) [`cls`, `seg`]
- [Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction](https://arxiv.org/pdf/1907.12704.pdf) [`unsupervised`, `cls`, `generation`, `seg`, `completion`]
- [SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences](https://openaccess.thecvf.com/content_ICCV_2019/papers/Behley_SemanticKITTI_A_Dataset_for_Semantic_Scene_Understanding_of_LiDAR_Sequences_ICCV_2019_paper.pdf) [`dataset`]
- [MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences](https://openaccess.thecvf.com/content_ICCV_2019/papers/Liu_MeteorNet_Deep_Learning_on_Dynamic_3D_Point_Cloud_Sequences_ICCV_2019_paper.pdf) [`cls`, `seg`, `flow estimation`; [Tensorflow](https://github.com/xingyul/meteornet)]
- [DeepGCNs: Can GCNs Go as Deep as CNNs?](https://openaccess.thecvf.com/content_ICCV_2019/papers/Li_DeepGCNs_Can_GCNs_Go_As_Deep_As_CNNs_ICCV_2019_paper.pdf) [`seg`; [Tensorflow](https://github.com/lightaime/deep_gcns)]
- [VV-NET: Voxel VAE Net with Group Convolutions for Point Cloud Segmentation](https://openaccess.thecvf.com/content_ICCV_2019/papers/Meng_VV-Net_Voxel_VAE_Net_With_Group_Convolutions_for_Point_Cloud_ICCV_2019_paper.pdf) [`seg`; [Github](https://github.com/xianyuMeng/VV-Net-Voxel-VAE-Net-with-Group-Convolutions-for-Point-Cloud-Segmentation)]
- [Interpolated Convolutional Networks for 3D Point Cloud Understanding](https://openaccess.thecvf.com/content_ICCV_2019/papers/Mao_Interpolated_Convolutional_Networks_for_3D_Point_Cloud_Understanding_ICCV_2019_paper.pdf) [`cls`, `seg`]
- [Dynamic Points Agglomeration for Hierarchical Point Sets Learning](https://openaccess.thecvf.com/content_ICCV_2019/papers/Liu_Dynamic_Points_Agglomeration_for_Hierarchical_Point_Sets_Learning_ICCV_2019_paper.pdf) [`cls`, `seg`]
- [ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statistics](https://openaccess.thecvf.com/content_ICCV_2019/papers/Zhang_ShellNet_Efficient_Point_Cloud_Convolutional_Neural_Networks_Using_Concentric_Shells_ICCV_2019_paper.pdf) [`cls`, `seg`; [Tensorflow](https://github.com/hkust-vgd/shellnet)]
- [Fast Point R-CNN](https://arxiv.org/pdf/1908.02990.pdf) [`det`]
- [Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data](https://openaccess.thecvf.com/content_ICCV_2019/papers/Uy_Revisiting_Point_Cloud_Classification_A_New_Benchmark_Dataset_and_Classification_ICCV_2019_paper.pdf) [`dataset`; `cls`; [Tensorflow](https://github.com/hkust-vgd/scanobjectnn)]
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://openaccess.thecvf.com/content_ICCV_2019/papers/Thomas_KPConv_Flexible_and_Deformable_Convolution_for_Point_Clouds_ICCV_2019_paper.pdf) [`cls`, `seg`; [code](https://github.com/HuguesTHOMAS/KPConv)]
- [Fully Convolutional Geometric Features](https://openaccess.thecvf.com/content_ICCV_2019/papers/Choy_Fully_Convolutional_Geometric_Features_ICCV_2019_paper.pdf) [`match`; [PyTorch](https://github.com/chrischoy/FCGF)]
- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://arxiv.org/pdf/1905.03304.pdf) [`registration`; [PyTorch](https://github.com/WangYueFt/dcp)]
- [DeepICP: An End-to-End Deep Neural Network for 3D Point Cloud Registration](https://arxiv.org/pdf/1905.04153.pdf) [`registration`]
- [Efficient and Robust Registration on the 3D Special Euclidean Group](https://openaccess.thecvf.com/content_ICCV_2019/papers/Bhattacharya_Efficient_and_Robust_Registration_on_the_3D_Special_Euclidean_Group_ICCV_2019_paper.pdf) [`registration`]
- [Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation](https://arxiv.org/pdf/1909.10469.pdf) [`seg`]
- [DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing](https://arxiv.org/pdf/1909.03669.pdf) [`cls`, `retrieval`, `seg`, `normal estimation`; [PyTorch](https://github.com/Yochengliu/DensePoint)]
- [DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds Defense](https://arxiv.org/pdf/1812.11017.pdf) [`cls`]
- [Efficient Learning on Point Clouds with Basis Point Sets](https://arxiv.org/pdf/1908.09186.pdf) [`cls`, `registration`; [PyTorch](https://github.com/sergeyprokudin/bps)]
- [PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows](https://arxiv.org/pdf/1906.12320.pdf) [`generation`, `reconstruction`; [Pytorch](https://github.com/stevenygd/PointFlow)
- [PU-GAN: a Point Cloud Upsampling Adversarial Network](https://arxiv.org/pdf/1907.10844) [`upsampling`, `reconstruction`; [Project](https://liruihui.github.io/publication/PU-GAN/)]
- [3D Point Cloud Learning for Large-scale Environment Analysis and Place Recognition](https://arxiv.org/pdf/1812.07050.pdf) [`retrieval`, `place recognition`]
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://arxiv.org/pdf/1904.09664.pdf) [`det`; [PyTorch](https://github.com/facebookresearch/votenet)]
- [Exploring the Limitations of Behavior Cloning for Autonomous Driving](https://arxiv.org/pdf/1904.08980.pdf) [`autonomous driving`; [Pytorch](https://github.com/felipecode/coiltraine)]
- CVPR
- [Deep Fitting Degree Scoring Network for Monocular 3D Object Detection](https://openaccess.thecvf.com/content_CVPR_2019/papers/Liu_Deep_Fitting_Degree_Scoring_Network_for_Monocular_3D_Object_Detection_CVPR_2019_paper.pdf) [`det`, `monocular`]
- [Multi-Task Multi-Sensor Fusion for 3D Object Detection](https://openaccess.thecvf.com/content_CVPR_2019/papers/Liang_Multi-Task_Multi-Sensor_Fusion_for_3D_Object_Detection_CVPR_2019_paper.pdf) [`det`]
- [LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention](https://openaccess.thecvf.com/content_CVPR_2020/papers/Yin_LiDAR-Based_Online_3D_Video_Object_Detection_With_Graph-Based_Message_Passing_CVPR_2020_paper.pdf) [`det`; [Github](https://github.com/yinjunbo/3DVID)]
- [TopNet: Structural Point Cloud Decoder](https://openaccess.thecvf.com/content_CVPR_2019/papers/Tchapmi_TopNet_Structural_Point_Cloud_Decoder_CVPR_2019_paper.pdf) [`completion`; [Github](https://github.com/lynetcha/completion3d)]
- [FlowNet3D: Learning Scene Flow in 3D Point Clouds](https://openaccess.thecvf.com/content_CVPR_2019/papers/Liu_FlowNet3D_Learning_Scene_Flow_in_3D_Point_Clouds_CVPR_2019_paper.pdf) [`scene flow`; [Tensorflow](https://github.com/xingyul/flownet3d)]
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://openaccess.thecvf.com/content_CVPR_2019/papers/Mescheder_Occupancy_Networks_Learning_3D_Reconstruction_in_Function_Space_CVPR_2019_paper.pdf) [`reconstruction`]
- [Associatively Segmenting Instances and Semantics in Point Clouds](https://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Associatively_Segmenting_Instances_and_Semantics_in_Point_Clouds_CVPR_2019_paper.pdf) [`seg`; [Tensorflow](https://github.com/WXinlong/ASIS)]
- [3D Point Capsule Networks](https://openaccess.thecvf.com/content_CVPR_2019/papers/Zhao_3D_Point_Capsule_Networks_CVPR_2019_paper.pdf) [`autoencoder`; [PyTorch](https://github.com/yongheng1991/3D-point-capsule-networks)]
- [Patch-based Progressive 3D Point Set Upsampling](https://openaccess.thecvf.com/content_CVPR_2019/papers/Yifan_Patch-Based_Progressive_3D_Point_Set_Upsampling_CVPR_2019_paper.pdf) [`upsampling`; [Tensorflow](https://github.com/yifita/3PU), [PyTorch](https://github.com/yifita/3PU_pytorch)]
- [Generating 3D Adversarial Point Clouds](https://openaccess.thecvf.com/content_CVPR_2019/papers/Xiang_Generating_3D_Adversarial_Point_Clouds_CVPR_2019_paper.pdf) [`adversary`; [Tensorflow](https://github.com/xiangchong1/3d-adv-pc)]
- [RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion](https://openaccess.thecvf.com/content_CVPR_2019/papers/Sarmad_RL-GAN-Net_A_Reinforcement_Learning_Agent_Controlled_GAN_Network_for_Real-Time_CVPR_2019_paper.pdf) [`completion`; [PyTorch](https://github.com/iSarmad/RL-GAN-Net)]
- [GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud](https://openaccess.thecvf.com/content_CVPR_2019/papers/Yi_GSPN_Generative_Shape_Proposal_Network_for_3D_Instance_Segmentation_in_CVPR_2019_paper.pdf) [`seg`; [Tensorflow](https://github.com/ericyi/GSPN)]
- [JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds with Multi-Task Pointwise Networks and Multi-Value Conditional Random Fields](https://openaccess.thecvf.com/content_CVPR_2019/papers/Pham_JSIS3D_Joint_Semantic-Instance_Segmentation_of_3D_Point_Clouds_With_Multi-Task_CVPR_2019_paper.pdf) [`seg`; [PyTorch](https://github.com/pqhieu/jsis3d)]
- [3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans](https://openaccess.thecvf.com/content_CVPR_2019/papers/Hou_3D-SIS_3D_Semantic_Instance_Segmentation_of_RGB-D_Scans_CVPR_2019_paper.pdf) [`seg`; [PyTorch](https://github.com/Sekunde/3D-SIS)]
- [Learning Transformation Synchronization](https://openaccess.thecvf.com/content_CVPR_2019/papers/Huang_Learning_Transformation_Synchronization_CVPR_2019_paper.pdf) [`transformation synchronization`, `registration`; [PyTorch](https://github.com/xiangruhuang/Learning2Sync)]
- [SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration without Correspondences](https://openaccess.thecvf.com/content_CVPR_2019/papers/Le_SDRSAC_Semidefinite-Based_Randomized_Approach_for_Robust_Point_Cloud_Registration_Without_CVPR_2019_paper.pdf) [`registration`; [Github](https://github.com/intellhave/SDRSAC)]
- [Learning Transformation Synchronization](https://openaccess.thecvf.com/content_CVPR_2019/papers/Huang_Learning_Transformation_Synchronization_CVPR_2019_paper.pdf) [`reconstruction`; [PyTorch](https://github.com/xiangruhuang/Learning2Sync)]
- [3D Local Features for Direct Pairwise Registration](https://openaccess.thecvf.com/content_CVPR_2019/papers/Deng_3D_Local_Features_for_Direct_Pairwise_Registration_CVPR_2019_paper.pdf) [`registration`]
- [DeepMapping: Unsupervised Map Estimation From Multiple Point Clouds](https://openaccess.thecvf.com/content_CVPR_2019/papers/Ding_DeepMapping_Unsupervised_Map_Estimation_From_Multiple_Point_Clouds_CVPR_2019_paper.pdf) [`registration`; [Github](https://github.com/ai4ce/DeepMapping)]
- [Relation-Shape Convolutional Neural Network for Point Cloud Analysis](https://openaccess.thecvf.com/content_CVPR_2019/papers/Liu_Relation-Shape_Convolutional_Neural_Network_for_Point_Cloud_Analysis_CVPR_2019_paper.pdf) [`cls`, `seg`, `normal estimation`; [PyTorch](https://github.com/Yochengliu/Relation-Shape-CNN)]
- [Modeling Local Geometric Structure of
3D Point Clouds using Geo-CNN](https://openaccess.thecvf.com/content_CVPR_2019/papers/Lan_Modeling_Local_Geometric_Structure_of_3D_Point_Clouds_Using_Geo-CNN_CVPR_2019_paper.pdf) [`cls`, `det`; [Tensorflow](https://github.com/voidrank/Geo-CNN)]
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://openaccess.thecvf.com/content_CVPR_2019/papers/Choy_4D_Spatio-Temporal_ConvNets_Minkowski_Convolutional_Neural_Networks_CVPR_2019_paper.pdf) [`seg`; [PyTorch](https://github.com/chrischoy/SpatioTemporalSegmentation)]
- [PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval](https://openaccess.thecvf.com/content_CVPR_2019/papers/Zhang_PCAN_3D_Attention_Map_Learning_Using_Contextual_Information_for_Point_CVPR_2019_paper.pdf) [`retrieval`; [Tensorflow](https://github.com/XLechter/PCAN)]
- [Attentional PointNet for 3D-Object Detection in Point Clouds](https://openaccess.thecvf.com/content_CVPRW_2019/papers/WAD/Paigwar_Attentional_PointNet_for_3D-Object_Detection_in_Point_Clouds_CVPRW_2019_paper.pdf) [`det`; [PyTorch](https://github.com/anshulpaigwar/Attentional-PointNet)]
- [Octree guided CNN with Spherical Kernels for 3D Point Clouds](https://openaccess.thecvf.com/content_CVPR_2019/papers/Lei_Octree_Guided_CNN_With_Spherical_Kernels_for_3D_Point_Clouds_CVPR_2019_paper.pdf) [`cls`, `seg`; [Github](https://github.com/hlei-ziyan/psicnn)]
- [A-CNN: Annularly Convolutional Neural Networks on Point Clouds](https://openaccess.thecvf.com/content_CVPR_2019/papers/Komarichev_A-CNN_Annularly_Convolutional_Neural_Networks_on_Point_Clouds_CVPR_2019_paper.pdf) [`cls`, `seg`; [Tensorflow](https://github.com/artemkomarichev/a-cnn)]
- [ClusterNet: Deep Hierarchical Cluster Network with Rigorously Rotation-Invariant Representation for Point Cloud Analysis](https://openaccess.thecvf.com/content_CVPR_2019/papers/Chen_ClusterNet_Deep_Hierarchical_Cluster_Network_With_Rigorously_Rotation-Invariant_Representation_for_CVPR_2019_paper.pdf) [`cls`]
- [Graph Attention Convolution for Point Cloud Semantic Segmentation](https://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Graph_Attention_Convolution_for_Point_Cloud_Semantic_Segmentation_CVPR_2019_paper.pdf) [`seg`; [PyTorch-unofficial](https://github.com/yanx27/GACNet)]
- [PointWeb: Enhancing Local Neighborhood Features for Point Cloud Processing](https://openaccess.thecvf.com/content_CVPR_2019/papers/Zhao_PointWeb_Enhancing_Local_Neighborhood_Features_for_Point_Cloud_Processing_CVPR_2019_paper.pdf) [`seg`, `cls`; [PyTorch](https://github.com/hszhao/PointWeb)]
- [Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling](https://openaccess.thecvf.com/content_CVPR_2019/papers/Yang_Modeling_Point_Clouds_With_Self-Attention_and_Gumbel_Subset_Sampling_CVPR_2019_paper.pdf) [`cls`, `seg`, `gesture`]
- [Learning to Sample](https://arxiv.org/pdf/1812.01659.pdf) [`sample`, `cls`, `retrieval`, `reconstruction`; [Tensorflow](https://github.com/orendv/learning_to_sample)]
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://openaccess.thecvf.com/content_CVPR_2019/papers/Wu_PointConv_Deep_Convolutional_Networks_on_3D_Point_Clouds_CVPR_2019_paper.pdf) [`cls`, `seg`; [Tensorflow](https://github.com/DylanWusee/pointconv)]
- [The Perfect Match: 3D Point Cloud Matching With Smoothed Densities](https://openaccess.thecvf.com/content_CVPR_2019/papers/Gojcic_The_Perfect_Match_3D_Point_Cloud_Matching_With_Smoothed_Densities_CVPR_2019_paper.pdf) [`match`; [code](https://github.com/zgojcic/3DSmoothNet)]
- [PointNetLK: Point Cloud Registration using PointNet](https://arxiv.org/pdf/1903.05711.pdf) [`registration`; [PyTorch](https://github.com/hmgoforth/PointNetLK)]
- [PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud](http://openaccess.thecvf.com/content_CVPR_2019/papers/Shi_PointRCNN_3D_Object_Proposal_Generation_and_Detection_From_Point_Cloud_CVPR_2019_paper.pdf) [`det`; [PyTorch](https://github.com/sshaoshuai/PointRCNN)]
- [PointPillars: Fast Encoders for Object Detection From Point Clouds](http://openaccess.thecvf.com/content_CVPR_2019/papers/Lang_PointPillars_Fast_Encoders_for_Object_Detection_From_Point_Clouds_CVPR_2019_paper.pdf) [`det`; [Pytorch](https://github.com/nutonomy/second.pytorch)]
- [Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving](https://arxiv.org/pdf/1812.07179.pdf) [`depth estimation`, `det`; [github](https://github.com/mileyan/pseudo_lidar)]
- [ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving](https://arxiv.org/pdf/1811.12222.pdf) [`dataset`, `autonomous driving`]
- [Stereo R-CNN based 3D Object Detection for Autonomous Driving](https://arxiv.org/pdf/1902.09738.pdf) [`det`, `autonomous driving`; [github](https://github.com/HKUST-Aerial-Robotics/Stereo-RCNN)]
- [Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction](https://arxiv.org/pdf/1904.01690.pdf) [`det`, `autonomous driving`; [Tesorflow](https://github.com/kujason/monopsr)]
- [LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving](https://arxiv.org/pdf/1903.08701.pdf) [`det`]
- [GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving](https://arxiv.org/pdf/1903.10955.pdf) [`det`, `autonomous driving`]
- [L3-Net: Towards Learning based LiDAR Localization for Autonomous Driving](https://songshiyu01.github.io/pdf/L3Net_W.Lu_Y.Zhou_S.Song_CVPR2019.pdf) [`autonomous driving`]
- [Iterative Transformer Network for 3D Point Cloud](https://arxiv.org/pdf/1811.11209.pdf) [`pose`, `cls`, `seg`; [Tensorflow](https://github.com/wentaoyuan/it-net)]
- Others
- [End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds](http://proceedings.mlr.press/v100/zhou20a/zhou20a.pdf) [`det`; CoRL]
- [PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation](https://arxiv.org/pdf/1911.02744.pdf) [`domain adaptation`; [PyTorch](https://github.com/canqin001/PointDAN); NeurIPS]
- [Learning elementary structures for 3D shape generation and matching](https://papers.nips.cc/paper/2019/file/d360a502598a4b64b936683b44a5523a-Paper.pdf) [`generation`, `matching`; NeurIPS]
- [Self-Supervised Deep Learning on Point Clouds by Reconstructing Space](https://papers.nips.cc/paper/2019/file/993edc98ca87f7e08494eec37fa836f7-Paper.pdf) [`self-supervised, cls, seg`; NeurIPS]
- [Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds](https://arxiv.org/pdf/1906.01140.pdf) [`seg`; [Tensorflow](https://github.com/Yang7879/3D-BoNet); NeurIPS]
- [PRNet: Self-Supervised Learning for Partial-to-Partial Registration](http://papers.nips.cc/paper/9085-prnet-self-supervised-learning-for-partial-to-partial-registration.pdf) [`registration`, `cls`; [PyTorch](https://github.com/WangYueFt/prnet); NeurIPS]
- [Point-Voxel CNN for Efficient 3D Deep Learning](https://arxiv.org/pdf/1907.03739.pdf) [`seg`, `det`; [PyTorch](https://github.com/mit-han-lab/pvcnn); NeurIPS]
- [L2G Auto-encoder: Understanding Point Clouds by Local-to-Global Reconstruction with Hierarchical Self-Attention](https://www.cs.umd.edu/~zwicker/publications/L2GAutoEncoder-ACMMM19.pdf) [`autoencoder`; ACM MM]
- [Deep Cascade Generation on Point Sets](https://www.ijcai.org/Proceedings/2019/0517.pdf) [`generation`; [PyTorch](https://github.com/wkqscut/DCGNet); IJCAI]
- [A Polynomial-time Solution for Robust Registration with Extreme Outlier Rates](https://arxiv.org/pdf/1903.08588.pdf) [`registration`; RSS]
- [Dynamic Graph CNN for Learning on Point Clouds](https://arxiv.org/pdf/1801.07829.pdf) [`cls`, `seg`; [Github](https://github.com/WangYueFt/dgcnn); TOG]
- [SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud](https://arxiv.org/pdf/1809.08495.pdf) [`seg`; [Tensorflow](https://github.com/xuanyuzhou98/SqueezeSegV2); ICRA]
- [Frustum ConvNet: Sliding Frustums to Aggregate Local Point-Wise Features for Amodal 3D Object Detection](https://arxiv.org/pdf/1903.01864.pdf) [`det`; [PyTorch](https://github.com/zhixinwang/frustum-convnet); IROS]
- [RangeNet++: Fast and Accurate LiDAR Semantic Segmentation](https://www.researchgate.net/profile/Cyrill_Stachniss/publication/338937998_RangeNet_Fast_and_Accurate_LiDAR_Semantic_Segmentation/links/5f609d4ba6fdcc1164133ac9/RangeNet-Fast-and-Accurate-LiDAR-Semantic-Segmentation.pdf) [`seg`; [PyTorch](https://github.com/PRBonn/lidar-bonnetal); IROS]
- [IoU Loss for 2D/3D Object Detection](https://arxiv.org/pdf/1908.03851.pdf) [`det`; 3DV]
- [AlignNet-3D: Fast Point Cloud Registration of Partially Observed Objects](https://arxiv.org/pdf/1910.04668.pdf) [`registration`; [Tensorflow](https://github.com/grossjohannes/AlignNet-3D); 3DV]
- [Dense 3D Point Cloud Reconstruction Using a Deep Pyramid Network](https://val.cds.iisc.ac.in/papers/WACV19_Dense_PCR.pdf) [`reconstruction`; WACV]
- arXiv
- [Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection](https://arxiv.org/pdf/1908.09492.pdf) [`det`]
- [PCRNet: Point Cloud Registration Network using PointNet Encoding](https://arxiv.org/pdf/1908.07906.pdf) [`registration`; [PyTorch](https://github.com/vinits5/pcrnet_pytorch), [Tensorflow](https://github.com/vinits5/pcrnet)]
- [LSANet: Feature Learning on Point Sets by Local Spatial Aware Layer](https://arxiv.org/pdf/1905.05442.pdf) [`cls`, `seg`; [Tensorflow](https://github.com/LinZhuoChen/LSANet)]
- [Adversarial Sensor Attack on LiDAR-based Perception in Autonomous Driving](https://arxiv.org/pdf/1907.06826.pdf) [`autonomous driving`]
- [Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features](https://arxiv.org/pdf/1904.10014.pdf) [`cls`, `seg`; [Tensorflow](https://github.com/KuangenZhang/ldgcnn)]
## 2018
- CVPR
- [PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation](https://openaccess.thecvf.com/content_cvpr_2018/papers/Xu_PointFusion_Deep_Sensor_CVPR_2018_paper.pdf) [`det`]
- [Learning 3D Shape Completion From Laser Scan Data With Weak Supervision](https://openaccess.thecvf.com/content_cvpr_2018/papers/Stutz_Learning_3D_Shape_CVPR_2018_paper.pdf) [`completion`; [Github](https://github.com/davidstutz/cvpr2018-shape-completion)]
- [Deep Parametric Continuous Convolutional Neural Networks](https://openaccess.thecvf.com/content_cvpr_2018/papers_backup/Wang_Deep_Parametric_Continuous_CVPR_2018_paper.pdf) [`seg`, `motion estimation(lidar flow)`]
- [Attentional ShapeContextNet for Point Cloud Recognition](http://pages.ucsd.edu/~ztu/publication/cvpr18_ascn.pdf) [`cls`, `seg`]
- [A Papier-Mâché Approach to Learning 3D Surface Generation](https://openaccess.thecvf.com/content_cvpr_2018/papers/Groueix_A_Papier-Mache_Approach_CVPR_2018_paper.pdf) [`generation`; [PyTorch](https://github.com/ThibaultGROUEIX/AtlasNet)]
- [Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs](https://openaccess.thecvf.com/content_cvpr_2018/papers/Landrieu_Large-Scale_Point_Cloud_CVPR_2018_paper.pdf) [`seg`; [PyTorch](https://github.com/loicland/superpoint_graph)]
- [FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation](https://openaccess.thecvf.com/content_cvpr_2018/papers/Yang_FoldingNet_Point_Cloud_CVPR_2018_paper.pdf) [`autoencoder`, `unsupervised`; [code](https://www.merl.com/research/license#FoldingNet)]
- [FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis](https://arxiv.org/pdf/1706.05206.pdf) [`correspondence`, `seg`; [Tensorflow](https://github.com/nitika-verma/FeaStNet)]
- [PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition](https://openaccess.thecvf.com/content_cvpr_2018/papers/Uy_PointNetVLAD_Deep_Point_CVPR_2018_paper.pdf) [`retrieval`, `place recognition`; [Tensorflow](https://github.com/mikacuy/pointnetvlad)]
- [PU-Net: Point Cloud Upsampling Network](https://openaccess.thecvf.com/content_cvpr_2018/papers/Yu_PU-Net_Point_Cloud_CVPR_2018_paper.pdf) [`upsampling`; [Tensorflow](https://github.com/yulequan/PU-Net)]
- [SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation](https://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_SGPN_Similarity_Group_CVPR_2018_paper.pdf) [`seg`; [Tensorflow](https://github.com/laughtervv/SGPN)]
- [Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling](https://openaccess.thecvf.com/content_cvpr_2018/CameraReady/1573.pdf) [`cls`, `seg`; [code](http://www.merl.com/research/license#KCNet)]
- [Tangent Convolutions for Dense Prediction in 3D](http://vladlen.info/papers/tangent-convolutions.pdf) [`seg`; [Tensorflow](https://github.com/tatarchm/tangent_conv)]
- [PointGrid: A Deep Network for 3D Shape Understanding](https://openaccess.thecvf.com/content_cvpr_2018/papers/Le_PointGrid_A_Deep_CVPR_2018_paper.pdf) [`cls`, `seg`; [Tensorflow](https://github.com/trucleduc/PointGrid)]
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://openaccess.thecvf.com/content_cvpr_2018/papers/Graham_3D_Semantic_Segmentation_CVPR_2018_paper.pdf) [`seg`; [Github](https://github.com/facebookresearch/SparseConvNet)]
- [Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs](https://openaccess.thecvf.com/content_cvpr_2018/papers/Landrieu_Large-Scale_Point_Cloud_CVPR_2018_paper.pdf) [`seg`; [PyTorch](https://github.com/loicland/superpoint_graph)]
- [SPLATNet: Sparse Lattice Networks for Point Cloud Processing](https://openaccess.thecvf.com/content_cvpr_2018/papers/Su_SPLATNet_Sparse_Lattice_CVPR_2018_paper.pdf) [`seg`; [Caffe](https://github.com/NVlabs/splatnet)]
- [Pointwise Convolutional Neural Networks](https://openaccess.thecvf.com/content_cvpr_2018/papers/Hua_Pointwise_Convolutional_Neural_CVPR_2018_paper.pdf) [`cls`, `seg`; [Tensorflow](https://github.com/hkust-vgd/pointwise)]
- [SO-Net: Self-Organizing Network for Point Cloud Analysis](https://openaccess.thecvf.com/content_cvpr_2018/papers/Li_SO-Net_Self-Organizing_Network_CVPR_2018_paper.pdf) [`autoencoder`, `cls`, `seg`; [PyTorch](https://github.com/lijx10/SO-Net)]
- [Recurrent Slice Networks for 3D Segmentation of Point Clouds](https://openaccess.thecvf.com/content_cvpr_2018/papers/Huang_Recurrent_Slice_Networks_CVPR_2018_paper.pdf) [`seg`; [PyTorch](https://github.com/qianguih/RSNet/blob/master/README.md)]
- [PPFNet: Global Context Aware Local Features for Robust 3D Point Matching](https://openaccess.thecvf.com/content_cvpr_2018/papers/Deng_PPFNet_Global_Context_CVPR_2018_paper.pdf) [`registration`]
- [PIXOR: Real-Time 3D Object Detection From Point Clouds](http://openaccess.thecvf.com/content_cvpr_2018/papers/Yang_PIXOR_Real-Time_3D_CVPR_2018_paper.pdf) [`det`; [PyTorch](https://github.com/philip-huang/PIXOR)]
- [Frustum PointNets for 3D Object Detection From RGB-D Data](http://openaccess.thecvf.com/content_cvpr_2018/papers/Qi_Frustum_PointNets_for_CVPR_2018_paper.pdf) [`det`; [Tensorflow](https://github.com/charlesq34/frustum-pointnets)]
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhou_VoxelNet_End-to-End_Learning_CVPR_2018_paper.pdf) [`det`]
- [3D-RCNN: Instance-Level 3D Object Reconstruction via Render-and-Compare](http://openaccess.thecvf.com/content_cvpr_2018/papers/Kundu_3D-RCNN_Instance-Level_3D_CVPR_2018_paper.pdf) [`reconstruction`]
- [Multi-Level Fusion Based 3D Object Detection From Monocular Images](http://openaccess.thecvf.com/content_cvpr_2018/papers/Xu_Multi-Level_Fusion_Based_CVPR_2018_paper.pdf) [`det`]
- ECCV
- [Complex-YOLO: Real-time 3D Object Detection on Point Clouds](https://arxiv.org/pdf/1803.06199) [`det`; [PyTorch](https://github.com/AI-liu/Complex-YOLO); ECCVW]
- [3D-CODED : 3D Correspondences by Deep Deformation](http://www.vovakim.com/papers/18_ECCV_3DCODED.pdf) [`matching`; [PyTorch](https://github.com/ThibaultGROUEIX/3D-CODED)]
- [SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters](https://openaccess.thecvf.com/content_ECCV_2018/papers/Yifan_Xu_SpiderCNN_Deep_Learning_ECCV_2018_paper.pdf) [`cls`, `seg`; [Tensorflow](https://github.com/xyf513/SpiderCNN)]
- [3DContextNet: K-d Tree Guided Hierarchical Learning of Point Clouds Using Local and Global Contextual Cues](https://openaccess.thecvf.com/content_ECCVW_2018/papers/11131/Zeng_3DContextNet_K-d_Tree_Guided_Hierarchical_Learning_of_Point_Clouds_Using_ECCVW_2018_paper.pdf) [`seg`, `cls`]
- [Multiresolution Tree Networks for
3D Point Cloud Processing](https://openaccess.thecvf.com/content_ECCV_2018/papers/Matheus_Gadelha_Multiresolution_Tree_Networks_ECCV_2018_paper.pdf) [`cls`, `generation`; [PyTorch](https://github.com/matheusgadelha/MRTNet)]
- [HGMR: Hierarchical Gaussian Mixtures for
Adaptive 3D Registration](https://openaccess.thecvf.com/content_ECCV_2018/papers/Benjamin_Eckart_Fast_and_Accurate_ECCV_2018_paper.pdf) [`registration`; [unofficial code](https://github.com/somanshu25/GPU-Accelerated-Point-Cloud-Registration-Using-Hierarchical-GMM)]
- [EC-Net: an Edge-aware Point set Consolidation Network](https://arxiv.org/pdf/1807.06010.pdf) [`consolidation`; [Tensorflow](https://github.com/yulequan/EC-Net)]
- [Learning and Matching Multi-View Descriptors for Registration of Point Clouds](https://openaccess.thecvf.com/content_ECCV_2018/papers/Lei_Zhou_Learning_and_Matching_ECCV_2018_paper.pdf) [`registration`]
- [Local Spectral Graph Convolution for Point Set Feature Learning](https://arxiv.org/pdf/1803.05827.pdf) [`cls`, `seg`]
- [3D Recurrent Neural Networks with Context Fusion for Point Cloud Semantic Segmentation](https://openaccess.thecvf.com/content_ECCV_2018/papers/Xiaoqing_Ye_3D_Recurrent_Neural_ECCV_2018_paper.pdf) [`seg`]
- [Fully-Convolutional Point Networks for Large-Scale Point Clouds](https://openaccess.thecvf.com/content_ECCV_2018/papers/Dario_Rethage_Fully-Convolutional_Point_Networks_ECCV_2018_paper.pdf) [`seg`, `captioning`; [Tensorflow](https://github.com/drethage/fully-convolutional-point-network)]
- [PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors](https://openaccess.thecvf.com/content_ECCV_2018/papers/Tolga_Birdal_PPF-FoldNet_Unsupervised_Learning_ECCV_2018_paper.pdf) [`registration`; [PyTorch-unofficial](https://github.com/XuyangBai/PPF-FoldNet)]
- [Deep Continuous Fusion for Multi-Sensor 3D Object Detection](http://openaccess.thecvf.com/content_ECCV_2018/papers/Ming_Liang_Deep_Continuous_Fusion_ECCV_2018_paper.pdf) [`det`]
- [3DFeat-Net: Weakly Supervised Local 3D
Features for Point Cloud Registration](https://openaccess.thecvf.com/content_ECCV_2018/papers/Zi_Jian_Yew_3DFeat-Net_Weakly_Supervised_ECCV_2018_paper.pdf) [`match`, `registration`; [Tensorflow](https://github.com/yewzijian/3DFeatNet)]
- [Stereo Vision-based Semantic 3D Object and Ego-motion Tracking for Autonomous Driving](http://openaccess.thecvf.com/content_ECCV_2018/papers/Peiliang_LI_Stereo_Vision-based_Semantic_ECCV_2018_paper.pdf) [`autonomous driving`]
- Others
- [PointCNN: Convolution On X -Transformed Points](http://papers.neurips.cc/paper/7362-pointcnn-convolution-on-x-transformed-points.pdf) [`cls`, `seg`; [Tensorflow](https://github.com/yangyanli/PointCNN); NeurIPS]
- [Learning Representations and Generative Models for 3D Point Clouds](https://arxiv.org/pdf/1707.02392.pdf) [`autoencoder`; [Tensorflow](https://github.com/optas/latent_3d_points); ICML]
- [RGCNN: Regularized Graph CNN for Point Cloud Segmentation](https://arxiv.org/pdf/1806.02952.pdf) [`seg`, `cls`; [Tensorflow](https://github.com/tegusi/RGCNN); ACM MM]
- [PCN: Point Completion Network](https://arxiv.org/pdf/1808.00671.pdf) [`completion`; [Tensorflow](https://github.com/wentaoyuan/pcn); 3DV]
- [Iterative Global Similarity Points : A robust coarse-to-fine integration solution for pairwise 3D point cloud registration](https://arxiv.org/pdf/1808.03899.pdf) [`registration`; 3DV]
- [Semantic Classification of 3D Point Clouds with Multiscale Spherical Neighborhoods](https://arxiv.org/pdf/1808.00495.pdf) [`seg`; 3DV]
- [Guaranteed Outlier Removal for Point Cloud Registration with Correspondences](https://www.researchgate.net/profile/Alvaro_Parra4/publication/321074557_Guaranteed_Outlier_Removal_for_Point_Cloud_Registration_with_Correspondences/links/5d2700bd92851cf440790ce5/Guaranteed-Outlier-Removal-for-Point-Cloud-Registration-with-Correspondences.pdf) [`registration`; TPAMI]
- [Second: Sparsely embedded convolutional detection](https://www.mdpi.com/1424-8220/18/10/3337/pdf) [`det`; `Sensors`]
- [Rt3d: Real-time 3-d vehicle detection in lidar point cloud for autonomous driving](https://ieeexplore.ieee.org/abstract/document/#) [`det`, `autonomous driving`; IEEE Robotics and Automation Letters]
- [HDNET: Exploiting HD Maps for 3D Object Detection](http://proceedings.mlr.press/v87/yang18b/yang18b.pdf) [`det`, `autonomous driving`; CoRL]
- [Joint 3D Proposal Generation and Object Detection from View Aggregation](https://arxiv.org/pdf/1712.02294.pdf) [`det`, `autonomous driving`; IROS]
- [Flex-Convolution(Million-Scale Point-Cloud Learning Beyond Grid-Worlds)](https://arxiv.org/pdf/1803.07289.pdf) [`cls`, `seg`; [Tensorflow](https://github.com/cgtuebingen/Flex-Convolution); ACCV]
- [SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud](https://arxiv.org/pdf/1710.07368.pdf) [`seg`; [Tensorflow](https://github.com/BichenWuUCB/SqueezeSeg); ICRA]
- [Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Clouds](https://arxiv.org/pdf/1806.01759.pdf) [`seg`, `cls`, `normal estimation`; [Tensorflow](https://github.com/viscom-ulm/MCCNN); TOG]
- [Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction](https://arxiv.org/pdf/1706.07036.pdf) [`reconstruction`; [Tensorflow](https://github.com/chenhsuanlin/3D-point-cloud-generation); AAAI]
- arXiv
- [Spherical Convolutional Neural Network
for 3D Point Clouds](https://arxiv.org/pdf/1805.07872.pdf) [`cls`]
- [Point Convolutional Neural Networks by Extension Operators](https://arxiv.org/pdf/1803.10091.pdf) [`cls`, `seg`, `normal estimation`; [Tensorflow](https://github.com/matanatz/pcnn)]
- [PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation](https://arxiv.org/pdf/1807.00652.pdf) [`seg`; [Tensorflow](https://github.com/MVIG-SJTU/pointSIFT)]
- [Point Cloud GAN](https://arxiv.org/pdf/1810.05795.pdf) [`generation`; [PyTorch](https://github.com/chunliangli/Point-Cloud-GAN)]
- [Roarnet: A robust 3d object detection based on region approximation refinement](https://arxiv.org/pdf/1811.03818.pdf) [`det`]
- [Classification of Point Cloud Scenes with Multiscale Voxel Deep Network](https://arxiv.org/pdf/1804.03583.pdf) [`seg`]
## 2017
- CVPR
- [Fine-To-Coarse Global Registration of RGB-D Scans](https://openaccess.thecvf.com/content_cvpr_2017/papers/Halber_Fine-To-Coarse_Global_Registration_CVPR_2017_paper.pdf) [`registration`; [Github](https://github.com/mhalber/Fine-To-Coarse-Registration)]
- [Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis](https://arxiv.org/pdf/1612.00101.pdf) [`completion`; [Torch7](https://github.com/angeladai/cnncomplete)]
- [SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation](https://openaccess.thecvf.com/content_cvpr_2017/papers/Yi_SyncSpecCNN_Synchronized_Spectral_CVPR_2017_paper.pdf) [`seg`, `keypoints`; [Github](https://github.com/ericyi/SyncSpecCNN)]
- [A Point Set Generation Network for 3D Object Reconstruction From a Single Image](https://openaccess.thecvf.com/content_cvpr_2017/papers/Fan_A_Point_Set_CVPR_2017_paper.pdf) [`reconstruction`; [Tensorflow](https://github.com/fanhqme/PointSetGeneration)]
- [Multi-View 3D Object Detection Network for Autonomous Driving](http://openaccess.thecvf.com/content_cvpr_2017/papers/Chen_Multi-View_3D_Object_CVPR_2017_paper.pdf) [`det`, `autonomous driving`; [Tensorflow](https://github.com/bostondiditeam/MV3D)]
- [Deep MANTA: A Coarse-To-Fine Many-Task Network for Joint 2D and 3D Vehicle Analysis From Monocular Image](http://openaccess.thecvf.com/content_cvpr_2017/papers/Chabot_Deep_MANTA_A_CVPR_2017_paper.pdf) [`autonomous driving`]
- **[PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](http://openaccess.thecvf.com/content_cvpr_2017/papers/Qi_PointNet_Deep_Learning_CVPR_2017_paper.pdf)** [`cls`, `seg`; [Tensorflow](https://github.com/charlesq34/pointnet)]
- [3D Bounding Box Estimation Using Deep Learning and Geometry](http://openaccess.thecvf.com/content_cvpr_2017/papers/Mousavian_3D_Bounding_Box_CVPR_2017_paper.pdf) [`det`]
- [OctNet: Learning Deep 3D Representations at High Resolutions](http://openaccess.thecvf.com/content_cvpr_2017/papers/Riegler_OctNet_Learning_Deep_CVPR_2017_paper.pdf) [`cls`, `seg`, `orientation estimation`; [PyTorch](https://github.com/griegler/octnet)]
- [3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions](https://openaccess.thecvf.com/content_cvpr_2017/papers/Zeng_3DMatch_Learning_Local_CVPR_2017_paper.pdf) [`match`, `registration`; [project](http://3dmatch.cs.princeton.edu/)]
- [3D Point Cloud Registration for Localization using a Deep Neural Network Auto-Encoder](https://openaccess.thecvf.com/content_cvpr_2017/papers/Elbaz_3D_Point_Cloud_CVPR_2017_paper.pdf) [`registration`; [github](https://github.com/gilbaz/LORAX)]
- ICCV
- [High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference](https://openaccess.thecvf.com/content_ICCV_2017/papers/Han_High-Resolution_Shape_Completion_ICCV_2017_paper.pdf) [`completion`]
- [Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models](https://arxiv.org/pdf/1704.01222.pdf) [`cls`, `retrieval`, `seg`; [PyTorch-unofficial](https://github.com/fxia22/kdnet.pytorch)]
- [Learning Compact Geometric Features](https://openaccess.thecvf.com/content_ICCV_2017/papers/Khoury_Learning_Compact_Geometric_ICCV_2017_paper.pdf) [`registration`; [Github](https://github.com/marckhoury/CGF)]
- [2D-Driven 3D Object Detection in RGB-D Images](http://openaccess.thecvf.com/content_ICCV_2017/papers/Lahoud_2D-Driven_3D_Object_ICCV_2017_paper.pdf) [`det`]
- Others
- **[Pointnet++: Deep hierarchical feature learning on point sets in a metric space](http://papers.nips.cc/paper/7095-pointnet-deep-hierarchical-feature-learning-on-point-sets-in-a-metric-space.pdf)** [`cls`, `seg`; [Tensorflow](https://github.com/charlesq34/pointnet2); NIPS]
- [Deep Sets](https://papers.nips.cc/paper/2017/file/f22e4747da1aa27e363d86d40ff442fe-Paper.pdf) [[PyTorch](https://github.com/manzilzaheer/DeepSets); `cls`; NIPS]
- [3D Object Proposals Using Stereo Imagery for Accurate Object Class Detection](https://arxiv.org/pdf/1608.07711.pdf) [`det`, `autonomous driving`; TPAMI]
- [O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis](https://arxiv.org/pdf/1712.01537.pdf) [`cls`, `retrieval`, `seg`; [Github](https://github.com/microsoft/O-CNN); TOG]
- [Vote3deep: Fast object detection in 3d point clouds using efficient convolutional neural networks](https://arxiv.org/pdf/1609.06666.pdf) [`det`; ICRA]
- [3d fully convolutional network for vehicle detection in point cloud](https://arxiv.org/pdf/1611.08069.pdf) [`det`; [Tensorflow](https://github.com/yukitsuji/3D_CNN_tensorflow); IROS]
- [Shape Completion Enabled Robotic Grasping](https://arxiv.org/pdf/1609.08546.pdf) [`completion`; [Keras](https://github.com/CRLab/pc_object_completion_cnn); IROS]
- [SEGCloud: Semantic Segmentation of 3D Point Clouds](https://arxiv.org/pdf/1710.07563.pdf) [`seg`; 3DV]
## Before 2016
- 2016
- [Fast Global Registration](https://www.researchgate.net/profile/Vladlen_Koltun/publication/305983982_Fast_Global_Registration/links/57a8086908aefe6167bc8366/Fast-Global-Registration.pdf) [`registration`; ECCV; [Github](https://github.com/intel-isl/FastGlobalRegistration)]
- [Monocular 3D Object Detection for Autonomous Driving](https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Chen_Monocular_3D_Object_CVPR_2016_paper.pdf) [CVPR]
- [Volumetric and Multi-View CNNs for Object Classification on 3D Data](http://openaccess.thecvf.com/content_cvpr_2016/papers/Qi_Volumetric_and_Multi-View_CVPR_2016_paper.pdf) [CVPR]
- [Three-Dimensional Object Detection and Layout Prediction Using Clouds of Oriented Gradients](https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Ren_Three-Dimensional_Object_Detection_CVPR_2016_paper.pdf) [CVPR]
- [Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images](https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Song_Deep_Sliding_Shapes_CVPR_2016_paper.pdf) [CVPR]
- [Fpnn: Field probing neural networks for 3d data](http://papers.nips.cc/paper/6416-fpnn-field-probing-neural-networks-for-3d-data.pdf) [NIPS]
- [Vehicle Detection from 3D Lidar Using Fully Convolutional Network](https://arxiv.org/pdf/1608.07916) [RSS]
- 2015
- [Robust Reconstruction of Indoor Scenes](https://www.researchgate.net/profile/Vladlen_Koltun/publication/279751165_Robust_Reconstruction_of_Indoor_Scenes/links/5599867708ae5d8f393633dc/Robust-Reconstruction-of-Indoor-Scenes.pdf) [`reconstruction`; CVPR]
- [Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration](https://arxiv.org/pdf/1605.03344.pdf) [`registration`; TPAMI; [Github](https://github.com/yangjiaolong/Go-ICP)]
- [3D ShapeNets: A Deep Representation for Volumetric Shapes](https://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Wu_3D_ShapeNets_A_2015_CVPR_paper.pdf) [CVPR]
- [SUN RGB-D: A RGB-D Scene Understanding Benchmark Suite](https://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Song_SUN_RGB-D_A_2015_CVPR_paper.pdf) [CVPR]
- [Data-Driven 3D Voxel Patterns for Object Category Recognition](https://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Xiang_Data-Driven_3D_Voxel_2015_CVPR_paper.pdf) [CVPR]
- [Multi-view convolutional neural networks for 3d shape recognition](https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/Su_Multi-View_Convolutional_Neural_ICCV_2015_paper.pdf) [ICCV]
- [3d object proposals for accurate object class detection](http://papers.nips.cc/paper/5644-3d-object-proposals-for-accurate-object-class-detection.pdf) [NIPS]
- [Voting for Voting in Online Point Cloud Object](https://pdfs.semanticscholar.org/521f/688f1fadaaff81269040f13270e8ec1a14d4.pdf) [RSS]
- [Voxnet: A 3d convolutional neural network for real-time object recognition](https://www.ri.cmu.edu/pub_files/2015/9/voxnet_maturana_scherer_iros15.pdf) [IROS]
- 2014
- [Are Cars Just 3D Boxes? - Jointly Estimating the 3D Shape of Multiple Objects](https://www.cv-foundation.org/openaccess/content_cvpr_2014/papers/Zia_Are_Cars_Just_2014_CVPR_paper.pdf) [CVPR]
- [Sliding shapes for 3d object detection in depth images](https://pdfs.semanticscholar.org/832e/eaede4f697f005b007798fe0d04829f656b7.pdf) [ECCV]
- 2013
- [Vision meets robotics: The kitti dataset](https://journals.sagepub.com/doi/full/10.1177/0278364913491297) [IJRR]
- 2012
- [Are we ready for autonomous driving? the kitti vision benchmark suite](http://www.webmail.cvlibs.net/publications/Geiger2012CVPR.pdf) [CVPR]
- 2009
- [Fast point feature histograms (FPFH) for 3D registration](https://www.cvl.iis.u-tokyo.ac.jp/class2016/2016w/papers/6.3DdataProcessing/Rusu_FPFH_ICRA2009.pdf) [`registration`; ICRA]
- [Generalized-ICP](http://www.robots.ox.ac.uk/~avsegal/resources/papers/Generalized_ICP.pdf) [`registration`; RSS]
- 1992
- [A method for registration of 3-D shapes](https://www.researchgate.net/publication/3191994_A_method_for_registration_of_3-D_shapes_IEEE_Trans_Pattern_Anal_Mach_Intell) [`registration`; TPAMI]
- 1987
- [Least-squares fitting of two 3-D point sets](https://www.researchgate.net/publication/224378053_Least-squares_fitting_of_two_3-D_point_sets_IEEE_T_Pattern_Anal) [`registration`; TPAMI]
## Resources
- [https://github.com/Yochengliu/awesome-point-cloud-analysis](https://github.com/Yochengliu/awesome-point-cloud-analysis)
- [https://github.com/yinyunie/3D-Shape-Analysis-Paper-List](https://github.com/yinyunie/3D-Shape-Analysis-Paper-List)
- [https://github.com/NUAAXQ/awesome-point-cloud-analysis-2020](https://github.com/NUAAXQ/awesome-point-cloud-analysis-2020)
- [https://github.com/QingyongHu/SoTA-Point-Cloud](https://github.com/QingyongHu/SoTA-Point-Cloud)
- [https://github.com/timzhang642/3D-Machine-Learning](https://github.com/timzhang642/3D-Machine-Learning)
- [https://github.com/XuyangBai/awesome-point-cloud-registration](https://github.com/XuyangBai/awesome-point-cloud-registration)
- [https://github.com/weiweisun2018/awesome-point-clouds-registration](https://github.com/weiweisun2018/awesome-point-clouds-registration)
- [https://github.com/chaytonmin/Awesome-BEV-Perception-Multi-Cameras](https://github.com/chaytonmin/Awesome-BEV-Perception-Multi-Cameras)
- [https://github.com/dragonlong/Trending-in-3D-Vision](https://github.com/dragonlong/Trending-in-3D-Vision)
- [https://github.com/4DVLab/Vision-Centric-BEV-Perception](https://github.com/4DVLab/Vision-Centric-BEV-Perception)
- [https://github.com/autodriving-heart/Awesome-occupancy-perception](https://github.com/autodriving-heart/Awesome-occupancy-perception)
## Tools
- [Open3D](http://www.open3d.org/): [https://github.com/intel-isl/Open3D](https://github.com/intel-isl/Open3D)
- [PCL](https://pointclouds.org/): [https://github.com/PointCloudLibrary/pcl](https://github.com/PointCloudLibrary/pcl)
- [PCL-Python](https://python-pcl-fork.readthedocs.io/en/latest/): [https://github.com/strawlab/python-pcl](https://github.com/strawlab/python-pcl)
- [Torch-Points3D](https://arxiv.org/pdf/2010.04642.pdf): [https://github.com/nicolas-chaulet/torch-points3d](https://github.com/nicolas-chaulet/torch-points3d)
- [mmdetection3d](https://mmdetection3d.readthedocs.io/en/latest/): [https://github.com/open-mmlab/mmdetection3d](https://github.com/open-mmlab/mmdetection3d)
- [OpenPCDet](https://github.com/open-mmlab/OpenPCDet): [https://github.com/open-mmlab/OpenPCDet](https://github.com/open-mmlab/OpenPCDet)
- [PyTorch3D](https://arxiv.org/pdf/2007.08501.pdf): [https://github.com/facebookresearch/pytorch3d](https://github.com/facebookresearch/pytorch3d)
- [Minkowski Engine](https://github.com/NVIDIA/MinkowskiEngine): [https://github.com/NVIDIA/MinkowskiEngine](https://github.com/NVIDIA/MinkowskiEngine)
- [pointcloudset](https://joss.theoj.org/papers/10.21105/joss.03471#): [https://github.com/virtual-vehicle/pointcloudset](https://github.com/virtual-vehicle/pointcloudset)
## Software
- [CloudCompare](https://www.danielgm.net/cc/): [https://github.com/cloudcompare/cloudcompare](https://github.com/cloudcompare/cloudcompare)
- [Semantic Segmentation Editor](https://github.com/Hitachi-Automotive-And-Industry-Lab/semantic-segmentation-editor): [https://github.com/Hitachi-Automotive-And-Industry-Lab/semantic-segmentation-editor](https://github.com/Hitachi-Automotive-And-Industry-Lab/semantic-segmentation-editor)
- [MeshLab](https://www.meshlab.net/): [https://github.com/cnr-isti-vclab/meshlab](https://github.com/cnr-isti-vclab/meshlab)