Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/NUAAXQ/awesome-point-cloud-analysis-2023
A list of papers and datasets about point cloud analysis (processing) since 2017. Update every day!
https://github.com/NUAAXQ/awesome-point-cloud-analysis-2023
List: awesome-point-cloud-analysis-2023
Last synced: about 2 months ago
JSON representation
A list of papers and datasets about point cloud analysis (processing) since 2017. Update every day!
- Host: GitHub
- URL: https://github.com/NUAAXQ/awesome-point-cloud-analysis-2023
- Owner: NUAAXQ
- Fork: true (Yochengliu/awesome-point-cloud-analysis)
- Created: 2020-03-22T18:19:39.000Z (over 4 years ago)
- Default Branch: master
- Last Pushed: 2024-04-10T08:25:30.000Z (5 months ago)
- Last Synced: 2024-05-21T09:14:57.792Z (4 months ago)
- Homepage:
- Size: 828 KB
- Stars: 1,476
- Watchers: 68
- Forks: 191
- Open Issues: 5
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-artificial-intelligence-research - Point Cloud Analysis
README
# awesome-point-cloud-analysis [](https://awesome.re)
for anyone who wants to do research about 3D point cloud.
I will try to update this list everyday!!!
```diff
- Recent papers (from 2017)
```
# Table of Contents
- [2017](#2017)
- [2018](#2018)
- [2019](#2019)
- [2020](#2020) [CVPR: 72 papers; ECCV: 40 papers]
- [2021](#2021) [CVPR: 66 papers; ICCV: 76 papers]
- [2022](#2022) [CVPR: 78 papers (57 with code); ECCV: 28 papers (23 with code)]
- [2023](#2023) [CVPR: 16 papers (13 with code); ICCV: 9 papers (8 with code)]
Keywords
__`dat.`__: dataset | __`cls.`__: classification | __`rel.`__: retrieval | __`seg.`__: segmentation
__`det.`__: detection | __`tra.`__: tracking | __`pos.`__: pose | __`dep.`__: depth
__`reg.`__: registration | __`rec.`__: reconstruction | __`aut.`__: autonomous driving
__`oth.`__: other, including normal-related, correspondence, mapping, matching, alignment, compression, generative model...
Statistics: :fire: code is available & stars >= 100 | :star: citation >= 50
---
## 2017
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2017/papers/Qi_PointNet_Deep_Learning_CVPR_2017_paper.pdf)] PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. [[tensorflow](https://github.com/charlesq34/pointnet)][[pytorch](https://github.com/fxia22/pointnet.pytorch)] [__`cls.`__ __`seg.`__ __`det.`__] :fire: :star:
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2017/papers/Simonovsky_Dynamic_Edge-Conditioned_Filters_CVPR_2017_paper.pdf)] Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs. [__`cls.`__] :star:
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2017/papers/Yi_SyncSpecCNN_Synchronized_Spectral_CVPR_2017_paper.pdf)] SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation. [[torch](https://github.com/ericyi/SyncSpecCNN)] [__`seg.`__ __`oth.`__] :star:
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2017/papers/Dai_ScanNet_Richly-Annotated_3D_CVPR_2017_paper.pdf)] ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. [[project](http://www.scan-net.org/)][[git](http://www.scan-net.org/)] [__`dat.`__ __`cls.`__ __`rel.`__ __`seg.`__ __`oth.`__] :fire: :star:
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2017/papers/Mostegel_Scalable_Surface_Reconstruction_CVPR_2017_paper.pdf)] Scalable Surface Reconstruction from Point Clouds with Extreme Scale and Density Diversity. [__`oth.`__]
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2017/papers/Straub_Efficient_Global_Point_CVPR_2017_paper.pdf)] Efficient Global Point Cloud Alignment using Bayesian Nonparametric Mixtures. [[code]( http://people.csail.mit.edu/jstraub/)] [__`oth.`__]
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2017/papers/Vongkulbhisal_Discriminative_Optimization_Theory_CVPR_2017_paper.pdf)] Discriminative Optimization: Theory and Applications to Point Cloud Registration. [__`reg.`__]
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2017/papers/Elbaz_3D_Point_Cloud_CVPR_2017_paper.pdf)] 3D Point Cloud Registration for Localization using a Deep Neural Network Auto-Encoder. [[git](https://github.com/gilbaz/LORAX)] [__`reg.`__]
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2017/papers/Chen_Multi-View_3D_Object_CVPR_2017_paper.pdf)] Multi-View 3D Object Detection Network for Autonomous Driving. [[tensorflow](https://github.com/bostondiditeam/MV3D)] [__`det.`__ __`aut.`__] :fire: :star:
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2017/papers/Zeng_3DMatch_Learning_Local_CVPR_2017_paper.pdf)] 3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions. [[code](https://github.com/andyzeng/3dmatch-toolbox)] [__`dat.`__ __`pos.`__ __`reg.`__ __`rec.`__ __`oth.`__] :fire: :star:
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2017/papers/Riegler_OctNet_Learning_Deep_CVPR_2017_paper.pdf)] OctNet: Learning Deep 3D Representations at High Resolutions. [[torch](https://github.com/griegler/octnet)] [__`cls.`__ __`seg.`__ __`oth.`__] :fire: :star:
-
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2017/papers/Klokov_Escape_From_Cells_ICCV_2017_paper.pdf)] Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models. [[pytorch](https://github.com/fxia22/kdnet.pytorch)] [__`cls.`__ __`rel.`__ __`seg.`__] :star:
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2017/papers/Liu_3DCNN-DQN-RNN_A_Deep_ICCV_2017_paper.pdf)] 3DCNN-DQN-RNN: A Deep Reinforcement Learning Framework for Semantic Parsing of Large-scale 3D Point Clouds. [[code](https://github.com/CKchaos/scn2pointcloud_tool)] [__`seg.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2017/papers/Park_Colored_Point_Cloud_ICCV_2017_paper.pdf)] Colored Point Cloud Registration Revisited. [__`reg.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2017/papers/Nan_PolyFit_Polygonal_Surface_ICCV_2017_paper.pdf)] PolyFit: Polygonal Surface Reconstruction from Point Clouds. [[code](https://github.com/LiangliangNan/PolyFit)] [__`rec.`__] :fire:
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2017/papers/Ladicky_From_Point_Clouds_ICCV_2017_paper.pdf)] From Point Clouds to Mesh using Regression. [__`rec.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2017/papers/Qi_3D_Graph_Neural_ICCV_2017_paper.pdf)] 3D Graph Neural Networks for RGBD Semantic Segmentation. [[pytorch](https://github.com/yanx27/3DGNN_pytorch)] [__`seg.`__]
-
- [[NeurIPS](https://papers.nips.cc/paper/7095-pointnet-deep-hierarchical-feature-learning-on-point-sets-in-a-metric-space)] PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. [[tensorflow](https://github.com/charlesq34/pointnet2)][[pytorch](https://github.com/erikwijmans/Pointnet2_PyTorch)] [__`cls.`__ __`seg.`__] :fire: :star:
- [[NeurIPS](https://papers.nips.cc/paper/6931-deep-sets)] Deep Sets. [[pytorch](https://github.com/manzilzaheer/DeepSets)] [__`cls.`__] :star:
-
- [[ICRA](https://ieeexplore.ieee.org/document/7989161)] Vote3Deep: Fast object detection in 3D point clouds using efficient convolutional neural networks. [[code](https://github.com/lijiannuist/Vote3Deep_lidar)] [__`det.`__ __`aut.`__] :star:
- [[ICRA](https://ieeexplore.ieee.org/document/7989591)] Fast segmentation of 3D point clouds: A paradigm on LiDAR data for autonomous vehicle applications. [[code](https://github.com/VincentCheungM/Run_based_segmentation)] [__`seg.`__ __`aut.`__]
- [[ICRA](https://ieeexplore.ieee.org/document/7989618)] SegMatch: Segment based place recognition in 3D point clouds. [__`seg.`__ __`oth.`__]
- [[ICRA](https://ieeexplore.ieee.org/document/7989664)] Using 2 point+normal sets for fast registration of point clouds with small overlap. [__`reg.`__]
-
- [[IROS](https://ieeexplore.ieee.org/document/8202234)] Car detection for autonomous vehicle: LIDAR and vision fusion approach through deep learning framework. [__`det.`__ __`aut.`__]
- [[IROS](https://ieeexplore.ieee.org/document/8202239)] 3D object classification with point convolution network. [__`cls.`__]
- [[IROS](https://ieeexplore.ieee.org/document/8205955)] 3D fully convolutional network for vehicle detection in point cloud. [[tensorflow](https://github.com/yukitsuji/3D_CNN_tensorflow)] [__`det.`__ __`aut.`__] :fire: :star:
- [[IROS](https://ieeexplore.ieee.org/document/8206488)] Deep learning of directional truncated signed distance function for robust 3D object recognition. [__`det.`__ __`pos.`__]
- [[IROS](https://ieeexplore.ieee.org/document/8206584)] Analyzing the quality of matched 3D point clouds of objects. [__`oth.`__]
-
- [[3DV](http://segcloud.stanford.edu/segcloud_2017.pdf)] SEGCloud: Semantic Segmentation of 3D Point Clouds. [[project](http://segcloud.stanford.edu/)] [__`seg.`__ __`aut.`__] :star:
-
- [[TPAMI](https://ieeexplore.ieee.org/ielx7/34/8454009/08046026.pdf?tp=&arnumber=8046026&isnumber=8454009&ref=aHR0cHM6Ly93d3cuZ29vZ2xlLmNvbS8=)] Structure-aware Data Consolidation. [__`oth.`__]
- [[ICCV](https://ieeexplore.ieee.org/document/8237364)] Local-to-Global Point Cloud Registration Using a Dictionary of Viewpoint Descriptors. [__`reg.`__]
- [[ICCV](https://ieeexplore.ieee.org/document/8237553)] Point Set Registration with Global-Local Correspondence and Transformation Estimation. [__`reg.`__]
- [[AAAI](http://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14188)] Non-Rigid Point Set Registration with Robust Transformation Estimation under Manifold Regularization. [__`reg.`__]
---
## 2018
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Su_SPLATNet_Sparse_Lattice_CVPR_2018_paper.pdf)] SPLATNet: Sparse Lattice Networks for Point Cloud Processing. [[caffe](https://github.com/NVlabs/splatnet)] [__`seg.`__] :fire:
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Xie_Attentional_ShapeContextNet_for_CVPR_2018_paper.pdf)] Attentional ShapeContextNet for Point Cloud Recognition. [__`cls.`__ __`seg.`__]
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Shen_Mining_Point_Cloud_CVPR_2018_paper.pdf)] Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling. [[code](http://www.merl.com/research/license#KCNet)] [__`cls.`__ __`seg.`__]
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Yang_FoldingNet_Point_Cloud_CVPR_2018_paper.pdf)] FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation. [[code](http://www.merl.com/research/license#FoldingNet)] [__`cls.`__]
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Hua_Pointwise_Convolutional_Neural_CVPR_2018_paper.pdf)] Pointwise Convolutional Neural Networks. [[tensorflow](https://github.com/scenenn/pointwise)] [__`cls.`__ __`seg.`__]
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Yu_PU-Net_Point_Cloud_CVPR_2018_paper.pdf)] PU-Net: Point Cloud Upsampling Network. [[tensorflow](https://github.com/yulequan/PU-Net)] [__`rec.`__ __`oth.`__] :fire:
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Li_SO-Net_Self-Organizing_Network_CVPR_2018_paper.pdf)] SO-Net: Self-Organizing Network for Point Cloud Analysis. [[pytorch](https://github.com/lijx10/SO-Net)] [__`cls.`__ __`seg.`__] :fire: :star:
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Huang_Recurrent_Slice_Networks_CVPR_2018_paper.pdf)] Recurrent Slice Networks for 3D Segmentation of Point Clouds. [[pytorch](https://github.com/qianguih/RSNet)] [__`seg.`__]
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Graham_3D_Semantic_Segmentation_CVPR_2018_paper.pdf)] 3D Semantic Segmentation with Submanifold Sparse Convolutional Networks. [[pytorch](https://github.com/facebookresearch/SparseConvNet)] [__`seg.`__] :fire:
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Deep_Parametric_Continuous_CVPR_2018_paper.pdf)] Deep Parametric Continuous Convolutional Neural Networks. [__`seg.`__ __`aut.`__]
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Yang_PIXOR_Real-Time_3D_CVPR_2018_paper.pdf)] PIXOR: Real-time 3D Object Detection from Point Clouds. [[pytorch](https://github.com/ankita-kalra/PIXOR)] [__`det.`__ __`aut.`__]
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_SGPN_Similarity_Group_CVPR_2018_paper.pdf)] SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation. [[tensorflow](https://github.com/laughtervv/SGPN)] [__`seg.`__] :fire:
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Landrieu_Large-Scale_Point_Cloud_CVPR_2018_paper.pdf)] Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs. [[pytorch](https://github.com/loicland/superpoint_graph)] [__`seg.`__] :fire:
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhou_VoxelNet_End-to-End_Learning_CVPR_2018_paper.pdf)] VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection. [[tensorflow](https://github.com/tsinghua-rll/VoxelNet-tensorflow)] [__`det.`__ __`aut.`__] :fire: :star:
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Yun_Reflection_Removal_for_CVPR_2018_paper.pdf)] Reflection Removal for Large-Scale 3D Point Clouds. [__`oth.`__]
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Ge_Hand_PointNet_3D_CVPR_2018_paper.pdf)] Hand PointNet: 3D Hand Pose Estimation using Point Sets. [[pytorch](https://github.com/3huo/Hand-Pointnet)] [__`pos.`__]
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Uy_PointNetVLAD_Deep_Point_CVPR_2018_paper.pdf)] PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition. [[tensorflow](https://github.com/mikacuy/pointnetvlad.git)] [__`rel.`__] :fire:
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Roveri_A_Network_Architecture_CVPR_2018_paper.pdf)] A Network Architecture for Point Cloud Classification via Automatic Depth Images Generation. [__`cls.`__]
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Lawin_Density_Adaptive_Point_CVPR_2018_paper.pdf)] Density Adaptive Point Set Registration. [[code](https://github.com/felja633/DARE)] [__`reg.`__]
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Birdal_A_Minimalist_Approach_CVPR_2018_paper.pdf)] A Minimalist Approach to Type-Agnostic Detection of Quadrics in Point Clouds. [__`seg.`__]
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Vongkulbhisal_Inverse_Composition_Discriminative_CVPR_2018_paper.pdf)] Inverse Composition Discriminative Optimization for Point Cloud Registration. [__`reg.`__]
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Reddy_CarFusion_Combining_Point_CVPR_2018_paper.pdf)] CarFusion: Combining Point Tracking and Part Detection for Dynamic 3D Reconstruction of Vehicles. [__`tra.`__ __`det.`__ __`rec.`__]
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Deng_PPFNet_Global_Context_CVPR_2018_paper.pdf)] PPFNet: Global Context Aware Local Features for Robust 3D Point Matching. [__`oth.`__]
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Le_PointGrid_A_Deep_CVPR_2018_paper.pdf)] PointGrid: A Deep Network for 3D Shape Understanding. [[tensorflow](https://github.com/trucleduc/PointGrid)] [__`cls.`__ __`seg.`__]
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Xu_PointFusion_Deep_Sensor_CVPR_2018_paper.pdf)] PointFusion: Deep Sensor Fusion for 3D Bounding Box Estimation. [[code](https://github.com/malavikabindhi/CS230-PointFusion)] [__`det.`__ __`aut.`__]
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Qi_Frustum_PointNets_for_CVPR_2018_paper.pdf)] Frustum PointNets for 3D Object Detection from RGB-D Data. [[tensorflow](https://github.com/charlesq34/frustum-pointnets)] [__`det.`__ __`aut.`__] :fire: :star:
- [[CVPR](http://openaccess.thecvf.com/content_cvpr_2018/papers/Tatarchenko_Tangent_Convolutions_for_CVPR_2018_paper.pdf)] Tangent Convolutions for Dense Prediction in 3D. [[tensorflow](https://github.com/tatarchm/tangent_conv)] [__`seg.`__ __`aut.`__]
-
- [[ECCV](http://openaccess.thecvf.com/content_ECCV_2018/papers/Matheus_Gadelha_Multiresolution_Tree_Networks_ECCV_2018_paper.pdf)] Multiresolution Tree Networks for 3D Point Cloud Processing. [[pytorch](https://github.com/matheusgadelha/MRTNet)] [__`cls.`__]
- [[ECCV](http://openaccess.thecvf.com/content_ECCV_2018/papers/Lequan_Yu_EC-Net_an_Edge-aware_ECCV_2018_paper.pdf)] EC-Net: an Edge-aware Point set Consolidation Network. [[tensorflow](https://github.com/yulequan/EC-Net)] [__`oth.`__]
- [[ECCV](http://openaccess.thecvf.com/content_ECCV_2018/papers/Xiaoqing_Ye_3D_Recurrent_Neural_ECCV_2018_paper.pdf)] 3D Recurrent Neural Networks with Context Fusion for Point Cloud Semantic Segmentation. [__`seg.`__]
- [[ECCV](http://openaccess.thecvf.com/content_ECCV_2018/papers/Lei_Zhou_Learning_and_Matching_ECCV_2018_paper.pdf)] Learning and Matching Multi-View Descriptors for Registration of Point Clouds. [__`reg.`__]
- [[ECCV](http://openaccess.thecvf.com/content_ECCV_2018/papers/Zi_Jian_Yew_3DFeat-Net_Weakly_Supervised_ECCV_2018_paper.pdf)] 3DFeat-Net: Weakly Supervised Local 3D Features for Point Cloud Registration. [[tensorflow](https://github.com/yewzijian/3DFeatNet)] [__`reg.`__]
- [[ECCV](http://openaccess.thecvf.com/content_ECCV_2018/papers/Chu_Wang_Local_Spectral_Graph_ECCV_2018_paper.pdf)] Local Spectral Graph Convolution for Point Set Feature Learning. [[tensorflow](https://github.com/fate3439/LocalSpecGCN)] [__`cls.`__ __`seg.`__]
- [[ECCV](http://openaccess.thecvf.com/content_ECCV_2018/papers/Yifan_Xu_SpiderCNN_Deep_Learning_ECCV_2018_paper.pdf)] SpiderCNN: Deep Learning on Point Sets with Parameterized Convolutional Filters. [[tensorflow](https://github.com/xyf513/SpiderCNN)] [__`cls.`__ __`seg.`__]
- [[ECCV](http://openaccess.thecvf.com/content_ECCV_2018/papers/Yinlong_Liu_Efficient_Global_Point_ECCV_2018_paper.pdf)] Efficient Global Point Cloud Registration by Matching Rotation Invariant Features Through Translation Search. [__`reg.`__]
- [[ECCV](http://openaccess.thecvf.com/content_ECCV_2018/papers/Kejie_Li_Efficient_Dense_Point_ECCV_2018_paper.pdf)] Efficient Dense Point Cloud Object Reconstruction using Deformation Vector Fields. [__`rec.`__]
- [[ECCV](http://openaccess.thecvf.com/content_ECCV_2018/papers/Dario_Rethage_Fully-Convolutional_Point_Networks_ECCV_2018_paper.pdf)] Fully-Convolutional Point Networks for Large-Scale Point Clouds. [[tensorflow](https://github.com/drethage/fully-convolutional-point-network)] [__`seg.`__ __`oth.`__]
- [[ECCV](http://openaccess.thecvf.com/content_ECCV_2018/papers/Ming_Liang_Deep_Continuous_Fusion_ECCV_2018_paper.pdf)] Deep Continuous Fusion for Multi-Sensor 3D Object Detection. [__`det.`__]
- [[ECCV](http://openaccess.thecvf.com/content_ECCV_2018/papers/Benjamin_Eckart_Fast_and_Accurate_ECCV_2018_paper.pdf)] HGMR: Hierarchical Gaussian Mixtures for Adaptive 3D Registration. [__`reg.`__]
- [[ECCV](http://openaccess.thecvf.com/content_ECCV_2018/papers/Liuhao_Ge_Point-to-Point_Regression_PointNet_ECCV_2018_paper.pdf)] Point-to-Point Regression PointNet for 3D Hand Pose Estimation. [__`pos.`__]
- [[ECCV](http://openaccess.thecvf.com/content_ECCV_2018/papers/Tolga_Birdal_PPF-FoldNet_Unsupervised_Learning_ECCV_2018_paper.pdf)] PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors. [__`oth.`__]
- [[ECCVW](http://openaccess.thecvf.com/content_ECCVW_2018/papers/11131/Zeng_3DContextNet_K-d_Tree_Guided_Hierarchical_Learning_of_Point_Clouds_Using_ECCVW_2018_paper.pdf)] 3DContextNet: K-d Tree Guided Hierarchical Learning of Point Clouds Using Local and Global Contextual Cues. [__`cls.`__ __`seg.`__]
- [[ECCVW](http://openaccess.thecvf.com/content_ECCVW_2018/papers/11131/Ali_YOLO3D_End-to-end_real-time_3D_Oriented_Object_Bounding_Box_Detection_from_ECCVW_2018_paper.pdf)] YOLO3D: End-to-end real-time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloud. [__`det.`__ __`aut.`__]
-
- [[AAAI](https://aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16530/16302)] Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction. [[tensorflow](https://github.com/chenhsuanlin/3D-point-cloud-generation)] [__`rec.`__] :fire:
- [[AAAI](https://ai.tencent.com/ailab/media/publications/aaai/junzhou_-AAAI-Adaptive_Graph_Convolutional_Neural_NetworksI.pdf)] Adaptive Graph Convolutional Neural Networks. [__`cls.`__]
-
- [[NeurIPS](https://papers.nips.cc/paper/7545-unsupervised-learning-of-shape-and-pose-with-differentiable-point-clouds)] Unsupervised Learning of Shape and Pose with Differentiable Point Clouds. [[tensorflow](https://github.com/eldar/differentiable-point-clouds)] [__`pos.`__]
- [[NeurIPS](https://papers.nips.cc/paper/7362-pointcnn-convolution-on-x-transformed-points)] PointCNN: Convolution On X-Transformed Points. [[tensorflow](https://github.com/yangyanli/PointCNN)][[pytorch](https://github.com/hxdengBerkeley/PointCNN.Pytorch)] [__`cls.`__ __`seg.`__] :fire:
-
- [[ICML](https://arxiv.org/abs/1707.02392)] Learning Representations and Generative Models for 3D Point Clouds. [[code](https://github.com/optas/latent_3d_points)] [__`oth.`__] :fire:
-
- [[TOG](https://dl.acm.org/ft_gateway.cfm?id=3201301&ftid=1991771&dwn=1&CFID=155708095&CFTOKEN=598df826a5b545a7-3E7CE91C-DE12-F588-FAEEF2551115E64E)] Point Convolutional Neural Networks by Extension Operators. [[tensorflow](https://github.com/matanatz/pcnn)] [__`cls.`__ __`seg.`__]
- [[SIGGRAPH](https://arxiv.org/abs/1803.09263)] P2P-NET: Bidirectional Point Displacement Net for Shape Transform. [[tensorflow](https://github.com/kangxue/P2P-NET)] [__`oth.`__]
- [[SIGGRAPH Asia](https://arxiv.org/abs/1806.01759)] Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Clouds. [[tensorflow](https://github.com/viscom-ulm/MCCNN)] [__`cls.`__ __`seg.`__ __`oth.`__]
- [[SIGGRAPH](https://arxiv.org/abs/1706.04496)] Learning local shape descriptors from part correspondences with multi-view convolutional networks. [[project](https://people.cs.umass.edu/~hbhuang/local_mvcnn/index.html)] [__`seg.`__ __`oth.`__]
-
- [[MM](https://arxiv.org/abs/1808.07659)] PVNet: A Joint Convolutional Network of Point Cloud and Multi-View for 3D Shape Recognition. [__`cls.`__ __`rel.`__]
- [[MM](https://arxiv.org/abs/1806.02952)] RGCNN: Regularized Graph CNN for Point Cloud Segmentation. [[tensorflow](https://github.com/tegusi/RGCNN)] [__`seg.`__]
- [[MM](https://arxiv.org/abs/1804.10783)] Hybrid Point Cloud Attribute Compression Using Slice-based Layered Structure and Block-based Intra Prediction. [__`oth.`__]
-
- [[ICRA](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8462884)] End-to-end Learning of Multi-sensor 3D Tracking by Detection. [__`det.`__ __`tra.`__ __`aut.`__]
- [[ICRA](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8460837)] Multi-View 3D Entangled Forest for Semantic Segmentation and Mapping. [__`seg.`__ __`oth.`__]
- [[ICRA](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8462926)] SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud. [[tensorflow](https://github.com/priyankanagaraj1494/Squeezseg)] [__`seg.`__ __`aut.`__]
- [[ICRA](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8461257)] Robust Real-Time 3D Person Detection for Indoor and Outdoor Applications. [__`det.`__]
- [[ICRA](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8461048)] High-Precision Depth Estimation with the 3D LiDAR and Stereo Fusion. [__`dep.`__ __`aut.`__]
- [[ICRA](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8461095)] Sampled-Point Network for Classification of Deformed Building Element Point Clouds. [__`cls.`__]
- [[ICRA](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8460532)] Gemsketch: Interactive Image-Guided Geometry Extraction from Point Clouds. [__`oth.`__]
- [[ICRA](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8460605)] Signature of Topologically Persistent Points for 3D Point Cloud Description. [__`oth.`__]
- [[ICRA](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8461232)] A General Pipeline for 3D Detection of Vehicles. [__`det.`__ __`aut.`__]
- [[ICRA](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8460716)] Robust and Fast 3D Scan Alignment Using Mutual Information. [__`oth.`__]
- [[ICRA](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8460940)] Delight: An Efficient Descriptor for Global Localisation Using LiDAR Intensities. [__`oth.`__]
- [[ICRA](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8460862)] Surface-Based Exploration for Autonomous 3D Modeling. [__`oth.`__ __`aut.`__]
- [[ICRA](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8460554)] Deep Lidar CNN to Understand the Dynamics of Moving Vehicles. [__`oth.`__ __`aut.`__]
- [[ICRA](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8460887)] Dex-Net 3.0: Computing Robust Vacuum Suction Grasp Targets in Point Clouds Using a New Analytic Model and Deep Learning. [__`oth.`__]
- [[ICRA](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8460639)] Real-Time Object Tracking in Sparse Point Clouds Based on 3D Interpolation. [__`tra.`__]
- [[ICRA](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8460825)] Robust Generalized Point Cloud Registration Using Hybrid Mixture Model. [__`reg.`__]
- [[ICRA](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8461049)] A General Framework for Flexible Multi-Cue Photometric Point Cloud Registration. [__`reg.`__]
- [[ICRA](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8461000)] Efficient Continuous-Time SLAM for 3D Lidar-Based Online Mapping. [__`oth.`__]
- [[ICRA](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8461102)] Direct Visual SLAM Using Sparse Depth for Camera-LiDAR System. [__`oth.`__]
- [[ICRA](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8460910)] Spatiotemporal Learning of Dynamic Gestures from 3D Point Cloud Data. [__`cls.`__]
- [[ICRA](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8460204)] Asynchronous Multi-Sensor Fusion for 3D Mapping and Localization. [__`oth.`__]
- [[ICRA](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8460834)] Complex Urban LiDAR Data Set. [[video](https://www.youtube.com/watch?v=IguZjmLf5V0&feature=youtu.be)] [__`dat.`__ __`oth.`__]
-
- [[IROS](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8593693)] CalibNet: Geometrically Supervised Extrinsic Calibration using 3D Spatial Transformer Networks.[[tensorflow](https://github.com/epiception/CalibNet)] [__`oth.`__ __`aut.`__]
- [[IROS](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8593839)] Dynamic Scaling Factors of Covariances for Accurate 3D Normal Distributions Transform Registration. [__`reg.`__]
- [[IROS](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8593733)] A 3D Laparoscopic Imaging System Based on Stereo-Photogrammetry with Random Patterns. [__`rec.`__ __`oth.`__]
- [[IROS](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8593558)] Robust Generalized Point Cloud Registration with Expectation Maximization Considering Anisotropic Positional Uncertainties. [__`reg.`__]
- [[IROS](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8594024)] Octree map based on sparse point cloud and heuristic probability distribution for labeled images. [__`oth.`__ __`aut.`__]
- [[IROS](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8593854)] PoseMap: Lifelong, Multi-Environment 3D LiDAR Localization. [__`oth.`__]
- [[IROS](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8593953)] Scan Context: Egocentric Spatial Descriptor for Place Recognition Within 3D Point Cloud Map. [__`oth.`__]
- [[IROS](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8594299)] LeGO-LOAM: Lightweight and Ground-Optimized Lidar Odometry and Mapping on Variable Terrain.[[code](https://github.com/RobustFieldAutonomyLab/LeGO-LOAM)] [__`pos.`__ __`oth.`__] :fire:
- [[IROS](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8593741)] Classification of Hanging Garments Using Learned Features Extracted from 3D Point Clouds. [__`cls.`__]
- [[IROS](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8594362)] Stereo Camera Localization in 3D LiDAR Maps. [__`pos.`__ __`oth.`__]
- [[IROS](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8594362)] Joint 3D Proposal Generation and Object Detection from View Aggregation. [__`det.`__] :star:
- [[IROS](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8594318)] Joint Point Cloud and Image Based Localization for Efficient Inspection in Mixed Reality. [__`oth.`__]
- [[IROS](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8593910)] Edge and Corner Detection for Unorganized 3D Point Clouds with Application to Robotic Welding. [__`det.`__ __`oth.`__]
- [[IROS](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8594175)] NDVI Point Cloud Generator Tool Using Low-Cost RGB-D Sensor. [[code](https://github.com/CTTCGeoLab/VI_ROS)][__`oth.`__]
- [[IROS](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8593837)] A 3D Convolutional Neural Network Towards Real-Time Amodal 3D Object Detection. [__`det.`__ __`pos.`__]
- [[IROS](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8594356)] Extracting Phenotypic Characteristics of Corn Crops Through the Use of Reconstructed 3D Models. [__`seg.`__ __`rec.`__]
- [[IROS](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8594514)] PCAOT: A Manhattan Point Cloud Registration Method Towards Large Rotation and Small Overlap. [__`reg.`__]
- [[IROS](https://arxiv.org/abs/1711.08241)] [[Tensorflow](https://github.com/sitzikbs/3DmFV-Net)]3DmFV: Point Cloud Classification and segmentation for unstructured 3D point clouds. [__`cls.`__ ]
- [[IROS](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8594042)] Seeing the Wood for the Trees: Reliable Localization in Urban and Natural Environments. [__`oth.`__ ]
-
- [[SENSORS](https://www.mdpi.com/1424-8220/18/10/3337)] SECOND: Sparsely Embedded Convolutional Detection. [[pytorch](https://github.com/traveller59/second.pytorch)] [__`det.`__ __`aut.`__] :fire:
-
- [[ACCV](https://arxiv.org/abs/1803.07289)] Flex-Convolution (Million-Scale Point-Cloud Learning Beyond Grid-Worlds). [[tensorflow](https://github.com/cgtuebingen/Flex-Convolution)] [__`seg.`__]
-
- [[3DV](https://arxiv.org/abs/1808.00671)] PCN: Point Completion Network. [[tensorflow](https://github.com/TonythePlaneswalker/pcn)] [__`reg.`__ __`oth.`__ __`aut.`__] :fire:
-
- [[ICASSP](https://arxiv.org/abs/1812.01711)] A Graph-CNN for 3D Point Cloud Classification. [[tensorflow](https://github.com/maggie0106/Graph-CNN-in-3D-Point-Cloud-Classification)] [__`cls.`__] :fire:
-
- [[ITSC](https://arxiv.org/pdf/1805.01195.pdf)] BirdNet: a 3D Object Detection Framework from LiDAR information. [__`det.`__ __`aut.`__]
-
- [[arXiv](https://arxiv.org/abs/1807.00652)] PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation. [[tensorflow](https://github.com/MVIG-SJTU/pointSIFT)] [__`seg.`__] :fire:
- [[arXiv](https://arxiv.org/abs/1805.07872)] Spherical Convolutional Neural Network for 3D Point Clouds. [__`cls.`__]
- [[arXiv](https://arxiv.org/abs/1811.07605)] Adversarial Autoencoders for Generating 3D Point Clouds. [__`oth.`__]
- [[arXiv](https://arxiv.org/abs/1811.11209)] Iterative Transformer Network for 3D Point Cloud. [__`cls.`__ __`seg.`__ __`pos.`__]
- [[arXiv](https://arxiv.org/abs/1811.12543)] Topology-Aware Surface Reconstruction for Point Clouds. [__`rec.`__]
- [[arXiv](https://arxiv.org/abs/1812.01402)] Inferring Point Clouds from Single Monocular Images by Depth Intermediation. [__`oth.`__]
- [[arXiv](https://arxiv.org/abs/1812.04302)] Deep RBFNet: Point Cloud Feature Learning using Radial Basis Functions. [__`cls.`__]
- [[arXiv](https://arxiv.org/abs/1812.05276)] IPOD: Intensive Point-based Object Detector for Point Cloud. [__`det.`__]
- [[arXiv](https://arxiv.org/abs/1812.11383)] Feature Preserving and Uniformity-controllable Point Cloud Simplification on Graph. [__`oth.`__]
- [[arXiv](https://arxiv.org/abs/1901.01060)] POINTCLEANNET: Learning to Denoise and Remove Outliers from Dense Point Clouds. [[pytorch](https://github.com/mrakotosaon/pointcleannet)] [__`oth.`__]
- [[arXiv](https://arxiv.org/abs/1803.06199)] Complex-YOLO: Real-time 3D Object Detection on Point Clouds. [[pytorch](https://github.com/AI-liu/Complex-YOLO)] [__`det.`__ __`aut.`__] :fire:
- [[arxiv](https://arxiv.org/abs/1811.03818)] RoarNet: A Robust 3D Object Detection based on RegiOn Approximation Refinement. [[tensorflow](https://github.com/Kiwoo/RoarNet)] [__`det.`__ __`aut.`__]
- [[arXiv](https://arxiv.org/abs/1812.11029)] Multi-column Point-CNN for Sketch Segmentation. [__`seg.`__]
- [[arXiv](https://arxiv.org/abs/1810.05591)] PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attention. [[project](https://liuziwei7.github.io/projects/PointGrow)] [__`oth.`__]
- [[arXiv](https://arxiv.org/pdf/1810.05795.pdf)] Point Cloud GAN. [[pytorch](https://github.com/chunliangli/Point-Cloud-GAN)] [__`oth.`__]
---
## 2019
- [[CVPR](http://export.arxiv.org/abs/1904.07601)] Relation-Shape Convolutional Neural Network for Point Cloud Analysis. [[pytorch](https://github.com/Yochengliu/Relation-Shape-CNN)] [__`cls.`__ __`seg.`__ __`oth.`__] :fire:
- [[CVPR](https://raoyongming.github.io/files/SFCNN.pdf)] Spherical Fractal Convolutional Neural Networks for Point Cloud Recognition. [__`cls.`__ __`seg.`__]
- [[CVPR](https://arxiv.org/abs/1811.11397)] DeepMapping: Unsupervised Map Estimation From Multiple Point Clouds. [[code](https://ai4ce.github.io/DeepMapping/)] [__`reg.`__]
- [[CVPR](https://arxiv.org/abs/1812.07179)] Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving. [[code](https://github.com/mileyan/pseudo_lidar)] [__`det.`__ __`dep.`__ __`aut.`__]
- [[CVPR](https://arxiv.org/abs/1812.04244)] PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud. [[pytorch](https://github.com/sshaoshuai/PointRCNN)] [__`det.`__ __`aut.`__] :fire:
- [[CVPR](https://arxiv.org/abs/1809.07016)] Generating 3D Adversarial Point Clouds. [[code](https://github.com/xiangchong1/3d-adv-pc)] [__`oth.`__]
- [[CVPR](https://arxiv.org/abs/1904.03375v1)] Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling. [__`cls.`__ __`seg.`__]
- [[CVPR](http://export.arxiv.org/abs/1904.08017)] A-CNN: Annularly Convolutional Neural Networks on Point Clouds. [[tensorflow](https://github.com/artemkomarichev/a-cnn)][__`cls.`__ __`seg.`__]
- [[CVPR](https://arxiv.org/abs/1811.07246)] PointConv: Deep Convolutional Networks on 3D Point Clouds. [[tensorflow](https://github.com/DylanWusee/pointconv)] [__`cls.`__ __`seg.`__] :fire:
- [[CVPR](https://arxiv.org/abs/1812.11647)] Path-Invariant Map Networks. [[tensorflow](https://github.com/zaiweizhang/path_invariance_map_network)] [__`seg.`__ __`oth.`__]
- [[CVPR](https://arxiv.org/abs/1812.02713)] PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding. [[code](https://github.com/daerduoCarey/partnet_dataset)] [__`dat.`__ __`seg.`__]
- [[CVPR](http://export.arxiv.org/abs/1901.00680)] GeoNet: Deep Geodesic Networks for Point Cloud Analysis. [__`cls.`__ __`rec.`__ __`oth.`__]
- [[CVPR](https://arxiv.org/abs/1902.09852)] Associatively Segmenting Instances and Semantics in Point Clouds. [[tensorflow](https://github.com/WXinlong/ASIS)] [__`seg.`__] :fire:
- [[CVPR](https://arxiv.org/abs/1811.08988)] Supervised Fitting of Geometric Primitives to 3D Point Clouds. [[tensorflow](https://github.com/csimstu2/SPFN)] [__`oth.`__]
- [[CVPR](https://arxiv.org/abs/1903.00343)] Octree guided CNN with Spherical Kernels for 3D Point Clouds. [[extension](https://arxiv.org/pdf/1909.09287.pdf)] [[code](https://github.com/hlei-ziyan/SPH3D-GCN)] [__`cls.`__ __`seg.`__]
- [[CVPR](https://arxiv.org/abs/1903.05711)] PointNetLK: Point Cloud Registration using PointNet. [[pytorch](https://github.com/hmgoforth/PointNetLK)] [__`reg.`__]
- [[CVPR](https://arxiv.org/abs/1904.00699v1)] JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds with Multi-Task Pointwise Networks and Multi-Value Conditional Random Fields. [[pytorch](https://github.com/pqhieu/JSIS3D)] [__`seg.`__]
- [[CVPR](https://arxiv.org/abs/1904.02113)] Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning. [__`seg.`__]
- [[CVPR](https://arxiv.org/abs/1812.05784)] PointPillars: Fast Encoders for Object Detection from Point Clouds. [[pytorch](https://github.com/nutonomy/second.pytorch)] [__`det.`__] :fire:
- [[CVPR](https://arxiv.org/abs/1811.11286)] Patch-based Progressive 3D Point Set Upsampling. [[tensorflow](https://github.com/yifita/3PU)] [__`oth.`__]
- [[CVPR](https://arxiv.org/abs/1904.09793)] PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrieval. [[code](https://github.com/XLechter/PCAN)] [__`rel.`__]
- [[CVPR](https://arxiv.org/abs/1903.00709)] PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation. [[pytorch](https://github.com/FoggYu/PartNet)] [__`dat.`__ __`seg.`__]
- [[CVPR](https://arxiv.org/abs/1806.02170)] PointFlowNet: Learning Representations for Rigid Motion Estimation from Point Clouds. [[code](https://github.com/aseembehl/pointflownet)] [__`det.`__ __`dat.`__ __`oth.`__]
- [[CVPR](https://arxiv.org/abs/1904.03483)] SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration without Correspondences. [[matlab](https://github.com/intellhave/SDRSAC)] [__`reg.`__]
- [[CVPR](https://arxiv.org/abs/1903.04019)] Deep Reinforcement Learning of Volume-guided Progressive View Inpainting for 3D Point Scene Completion from a Single Depth Image. [__`rec.`__ __`oth.`__]
- [[CVPR](https://arxiv.org/abs/1904.03461)] Embodied Question Answering in Photorealistic Environments with Point Cloud Perception. [__`oth.`__]
- [[CVPR](https://arxiv.org/abs/1812.10775v1)] 3D Point-Capsule Networks. [[pytorch](https://github.com/yongheng1991/3D-point-capsule-networks)] [__`cls.`__ __`rec.`__ __`oth.`__]
- [[CVPR](http://export.arxiv.org/abs/1904.08755)] 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. [[pytorch](https://github.com/StanfordVL/MinkowskiEngine)] [__`seg.`__] :fire:
- [[CVPR](https://arxiv.org/abs/1811.06879v2)] The Perfect Match: 3D Point Cloud Matching with Smoothed Densities. [[tensorflow](https://github.com/zgojcic/3DSmoothNet)] [__`oth.`__]
- [[CVPR](https://arxiv.org/abs/1811.10136)] FilterReg: Robust and Efficient Probabilistic Point-Set Registration using Gaussian Filter and Twist Parameterization. [[code](https://bitbucket.org/gaowei19951004/poser/src/master/)] [__`reg.`__]
- [[CVPR](https://arxiv.org/abs/1806.01411)] FlowNet3D: Learning Scene Flow in 3D Point Clouds. [__`oth.`__]
- [[CVPR](https://arxiv.org/abs/1811.07782)] Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN. [__`cls.`__ __`det.`__]
- [[CVPR](http://www.linliang.net/wp-content/uploads/2019/04/CVPR2019_PointClound.pdf)] ClusterNet: Deep Hierarchical Cluster Network with Rigorously Rotation-Invariant Representation for Point Cloud Analysis. [__`cls.`__]
- [[CVPR](http://jiaya.me/papers/pointweb_cvpr19.pdf)] PointWeb: Enhancing Local Neighborhood Features for Point Cloud Processing. [[pytorch](https://github.com/hszhao/PointWeb)] [__`cls.`__ __`seg.`__]
- [[CVPR](https://arxiv.org/abs/1904.12304)] RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion. [[code](https://github.com/iSarmad/RL-GAN-Net)] [__`oth.`__]
- [[CVPR](https://arxiv.org/abs/1903.05711)] PointNetLK: Robust & Efficient Point Cloud Registration using PointNet. [[pytorch](https://github.com/hmgoforth/PointNetLK)] [__`reg.`__]
- [[CVPR](https://www.researchgate.net/publication/332240602_Robust_Point_Cloud_Based_Reconstruction_of_Large-Scale_Outdoor_Scenes)] Robust Point Cloud Based Reconstruction of Large-Scale Outdoor Scenes. [[code](https://github.com/ziquan111/RobustPCLReconstruction)] [__`rec.`__]
- [[CVPR](https://arxiv.org/abs/1812.00709)] Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds using Convolutional Neural Networks. [[tensorflow](https://github.com/sitzikbs/Nesti-Net)] [__`oth.`__]
- [[CVPR](https://arxiv.org/abs/1812.03320)] GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud. [__`seg.`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Graph_Attention_Convolution_for_Point_Cloud_Semantic_Segmentation_CVPR_2019_paper.pdf)] Graph Attention Convolution for Point Cloud Semantic Segmentation. [__`seg.`__]
- [[CVPR](https://arxiv.org/abs/1812.02050)] Point-to-Pose Voting based Hand Pose Estimation using Residual Permutation Equivariant Layer. [__`pos.`__]
- [[CVPR](https://arxiv.org/abs/1903.08701v1)] LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving. [__`det.`__ __`aut.`__]
- [[CVPR](https://arxiv.org/pdf/1904.03498.pdf)] LP-3DCNN: Unveiling Local Phase in 3D Convolutional Neural Networks. [[project](https://sites.google.com/view/lp-3dcnn/home)] [__`cls.`__ __`seg.`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2019/papers/Duan_Structural_Relational_Reasoning_of_Point_Clouds_CVPR_2019_paper.pdf)] Structural Relational Reasoning of Point Clouds. [__`cls.`__ __`seg.`__]
- [[CVPR](https://arxiv.org/abs/1903.03322)] 3DN: 3D Deformation Network. [[tensorflow](https://github.com/laughtervv/3DN)] [__`rec.`__ __`oth.`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2019/papers/Speciale_Privacy_Preserving_Image-Based_Localization_CVPR_2019_paper.pdf)] Privacy Preserving Image-Based Localization. [__`pos.`__ __`oth.`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2019/html/Chang_Argoverse_3D_Tracking_and_Forecasting_With_Rich_Maps_CVPR_2019_paper.html)] Argoverse: 3D Tracking and Forecasting With Rich Maps.[__`tra.`__ __`aut.`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2019/papers/Giancola_Leveraging_Shape_Completion_for_3D_Siamese_Tracking_CVPR_2019_paper.pdf)] Leveraging Shape Completion for 3D Siamese Tracking. [[pytorch](https://github.com/SilvioGiancola/ShapeCompletion3DTracking)] [__`tra.`__ ]
- [[CVPRW](http://openaccess.thecvf.com/content_CVPRW_2019/papers/WAD/Paigwar_Attentional_PointNet_for_3D-Object_Detection_in_Point_Clouds_CVPRW_2019_paper.pdf)] Attentional PointNet for 3D-Object Detection in Point Clouds. [[pytorch](https://github.com/anshulpaigwar/Attentional-PointNet)] [__`cls.`__ __`det.`__ __`aut.`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2019/papers/Deng_3D_Local_Features_for_Direct_Pairwise_Registration_CVPR_2019_paper.pdf)] 3D Local Features for Direct Pairwise Registration. [__`reg.`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2019/papers/Dovrat_Learning_to_Sample_CVPR_2019_paper.pdf)] Learning to Sample. [[tensorflow](https://github.com/orendv/learning_to_sample)] [__`cls.`__ __`rec.`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2019/papers/Pittaluga_Revealing_Scenes_by_Inverting_Structure_From_Motion_Reconstructions_CVPR_2019_paper.pdf)] Revealing Scenes by Inverting Structure from Motion Reconstructions. [[code](https://github.com/francescopittaluga/invsfm)] [__`rec.`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2019/papers/Qiu_DeepLiDAR_Deep_Surface_Normal_Guided_Depth_Prediction_for_Outdoor_Scene_CVPR_2019_paper.pdf)] DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image. [[pytorch](https://github.com/JiaxiongQ/DeepLiDAR)] [__`dep.`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2019/papers/Gu_HPLFlowNet_Hierarchical_Permutohedral_Lattice_FlowNet_for_Scene_Flow_Estimation_on_CVPR_2019_paper.pdf)] HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Clouds. [[pytorch](https://github.com/laoreja/HPLFlowNet)] [__`oth.`__]
-
- [[ICCV](https://arxiv.org/abs/1904.09664v1)] Deep Hough Voting for 3D Object Detection in Point Clouds. [[pytorch](https://github.com/facebookresearch/votenet)] [[tensorflow](https://github.com/qq456cvb/VoteNet)] [__`det.`__] :fire:
- [[ICCV](https://arxiv.org/abs/1904.03751)] DeepGCNs: Can GCNs Go as Deep as CNNs? [[tensorflow](https://github.com/lightaime/deep_gcns)] [[pytorch]](https://github.com/lightaime/deep_gcns_torch) [__`seg.`__] :fire:
- [[ICCV](https://arxiv.org/pdf/1907.10844.pdf)] PU-GAN: a Point Cloud Upsampling Adversarial Network. [[tensorflow](https://github.com/liruihui/PU-GAN)] [__`oth.`__]
- [[ICCV](https://arxiv.org/pdf/1812.07050.pdf)] 3D Point Cloud Learning for Large-scale Environment Analysis and Place Recognition. [__`rel.`__ __`oth.`__]
- [[ICCV](https://arxiv.org/pdf/1906.12320.pdf)] PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows. [[pytorch](https://github.com/stevenygd/PointFlow)] [__`oth.`__]
- [[ICCV](https://arxiv.org/pdf/1907.12704.pdf)] Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction. [__`oth.`__]
- [[ICCV](https://drive.google.com/file/d/11GJzouV6jt_aOpvrJ8l3J5x_R_-m-Lg8/view)] SO-HandNet: Self-Organizing Network for 3D Hand Pose Estimation with Semi-supervised Learning. [[code](https://github.com/TerenceCYJ/SO-HandNet)] [__`pos.`__]
- [[ICCV](https://arxiv.org/abs/1812.11017)] DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds Defense. [__`oth.`__]
- [[ICCV](https://arxiv.org/abs/1908.04616)] Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data. [__`cls.`__ __`dat.`__] [[code](https://github.com/hkust-vgd/scanobjectnn)] [[dataset](https://hkust-vgd.github.io/scanobjectnn/)]
- [[ICCV](https://arxiv.org/abs/1904.08889)] KPConv: Flexible and Deformable Convolution for Point Clouds. [[tensorflow](https://github.com/HuguesTHOMAS/KPConv)] [__`cls.`__ __`seg.`__] :fire:
- [[ICCV](https://arxiv.org/pdf/1908.06295.pdf)] ShellNet: Efficient Point Cloud Convolutional Neural Networks using Concentric Shells Statistics. [[project](https://hkust-vgd.github.io/shellnet/)] [__`seg.`__]
- [[ICCV](https://arxiv.org/pdf/1908.04422.pdf)] Point-Based Multi-View Stereo Network. [[pytorch](https://github.com/callmeray/PointMVSNet)] [__`rec.`__]
- [[ICCV](https://arxiv.org/abs/1909.03669)] DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing. [[pytorch](https://github.com/Yochengliu/DensePoint)] [__`cls.`__ __`seg.`__ __`oth.`__]
- [[ICCV](https://arxiv.org/abs/1905.04153v2)] DeepICP: An End-to-End Deep Neural Network for 3D Point Cloud Registration. [__`reg.`__]
- [[ICCV](https://arxiv.org/pdf/1905.06292.pdf)] 3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions. [[pytorch](https://github.com/seowok/TreeGAN)] [__`oth.`__]
- [[ICCV](https://arxiv.org/pdf/1909.10469.pdf)] Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation. [__`seg.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2019/papers/Spezialetti_Learning_an_Effective_Equivariant_3D_Descriptor_Without_Supervision_ICCV_2019_paper.pdf)] Learning an Effective Equivariant 3D Descriptor Without Supervision. [__`oth.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2019/html/Choy_Fully_Convolutional_Geometric_Features_ICCV_2019_paper.html)] Fully Convolutional Geometric Features. [[pytorch](https://github.com/chrischoy/FCGF)] [__`reg.`__]
- [[ICCV](https://arxiv.org/pdf/1812.07050.pdf)] LPD-Net: 3D Point Cloud Learning for Large-Scale Place Recognition and Environment Analysis. [__`oth.`__ __`aut.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2019/papers/Hermosilla_Total_Denoising_Unsupervised_Learning_of_3D_Point_Cloud_Cleaning_ICCV_2019_paper.pdf)] Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaning. [[tensorflow](https://github.com/phermosilla/TotalDenoising)] [__`oth.`__]
- [[ICCV](https://arxiv.org/abs/1904.00229)] USIP: Unsupervised Stable Interest Point Detection from 3D Point Clouds. [[pytorch](https://github.com/lijx10/USIP)] [__`oth.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2019/papers/Mao_Interpolated_Convolutional_Networks_for_3D_Point_Cloud_Understanding_ICCV_2019_paper.pdf)] Interpolated Convolutional Networks for 3D Point Cloud Understanding. [__`cls.`__ __`seg.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2019/papers/Zheng_PointCloud_Saliency_Maps_ICCV_2019_paper.pdf)] PointCloud Saliency Maps. [[code](https://github.com/tianzheng4/PointCloud-Saliency-Maps)] [__`oth.`__]
- [[ICCV](https://arxiv.org/pdf/1907.10471.pdf)] STD: Sparse-to-Dense 3D Object Detector for Point Cloud. [__`det.`__ __`oth.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2019/papers/Golyanik_Accelerated_Gravitational_Point_Set_Alignment_With_Altered_Physical_Laws_ICCV_2019_paper.pdf)] Accelerated Gravitational Point Set Alignment with Altered Physical Laws. [__`reg.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2019/papers/Wang_Deep_Closest_Point_Learning_Representations_for_Point_Cloud_Registration_ICCV_2019_paper.pdf)] Deep Closest Point: Learning Representations for Point Cloud Registration. [__`reg.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2019/papers/Prokudin_Efficient_Learning_on_Point_Clouds_With_Basis_Point_Sets_ICCV_2019_paper.pdf)] Efficient Learning on Point Clouds with Basis Point Sets. [[code](https://github.com/sergeyprokudin/bps)] [__`cls.`__ __`reg.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2019/papers/Dai_PointAE_Point_Auto-Encoder_for_3D_Statistical_Shape_and_Texture_Modelling_ICCV_2019_paper.pdf)] PointAE: Point Auto-encoder for 3D Statistical Shape and Texture Modelling. [__`rec.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2019/papers/Jiang_Skeleton-Aware_3D_Human_Shape_Reconstruction_From_Point_Clouds_ICCV_2019_paper.pdf)] Skeleton-Aware 3D Human Shape Reconstruction From Point Clouds. [__`rec.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2019/papers/Liu_Dynamic_Points_Agglomeration_for_Hierarchical_Point_Sets_Learning_ICCV_2019_paper.pdf)] Dynamic Points Agglomeration for Hierarchical Point Sets Learning. [[pytorch](https://github.com/yuyi1005/DPAM)] [__`cls.`__ __`seg.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2019/papers/Hassani_Unsupervised_Multi-Task_Feature_Learning_on_Point_Clouds_ICCV_2019_paper.pdf)] Unsupervised Multi-Task Feature Learning on Point Clouds. [__`cls.`__ __`seg.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2019/papers/Meng_VV-Net_Voxel_VAE_Net_With_Group_Convolutions_for_Point_Cloud_ICCV_2019_paper.pdf)] VV-NET: Voxel VAE Net with Group Convolutions for Point Cloud Segmentation. [[tensorflow](https://github.com/xianyuMeng/VV-Net-Voxel-VAE-Net-with-Group-Convolutions-for-Point-Cloud-Segmentation)] [__`seg.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2019/papers/Nguyen_GraphX-Convolution_for_Point_Cloud_Deformation_in_2D-to-3D_Conversion_ICCV_2019_paper.pdf)] GraphX-Convolution for Point Cloud Deformation in 2D-to-3D Conversion. [[pytorch](https://github.com/justanhduc/graphx-conv)] [__`rec.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2019/papers/Liu_MeteorNet_Deep_Learning_on_Dynamic_3D_Point_Cloud_Sequences_ICCV_2019_paper.pdf)] MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences. [[code](https://github.com/xingyul/meteornet)] [__`cls.`__ __`seg.`__ __`oth.`__]
- [[ICCV](https://arxiv.org/abs/1908.02990)] Fast Point R-CNN. [__`det.`__ __`aut.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhou_Robust_Variational_Bayesian_Point_Set_Registration_ICCV_2019_paper.pdf)] Robust Variational Bayesian Point Set Registration. [__`reg.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2019/papers/Mehr_DiscoNet_Shapes_Learning_on_Disconnected_Manifolds_for_3D_Editing_ICCV_2019_paper.pdf)] DiscoNet: Shapes Learning on Disconnected Manifolds for 3D Editing. [__`rec.`__ __`oth.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2019/papers/Spezialetti_Learning_an_Effective_Equivariant_3D_Descriptor_Without_Supervision_ICCV_2019_paper.pdf)] Learning an Effective Equivariant 3D Descriptor Without Supervision. [__`oth.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2019/papers/Lahoud_3D_Instance_Segmentation_via_Multi-Task_Metric_Learning_ICCV_2019_paper.pdf)] 3D Instance Segmentation via Multi-Task Metric Learning. [[code](https://sites.google.com/view/3d-instance-mtml)] [__`seg.`__]
- [[ICCV](http://openaccess.thecvf.com/content_ICCV_2019/papers/Liu_3D_Face_Modeling_From_Diverse_Raw_Scan_Data_ICCV_2019_paper.pdf)] 3D Face Modeling From Diverse Raw Scan Data. [__`rec.`__]
- [[ICCVW](https://arxiv.org/abs/1909.12249)] Range Adaptation for 3D Object Detection in LiDAR. [__`det.`__ __`aut.`__]
-
- [[NeurIPS](https://arxiv.org/pdf/1901.08396.pdf)] Self-Supervised Deep Learning on Point Clouds by Reconstructing Space. [__`cls.`__ __`oth.`__]
- [[NeurIPS](https://arxiv.org/abs/1906.01140)] Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds. [[tensorflow](https://github.com/Yang7879/3D-BoNet)] [__`det.`__ __`seg.`__]
- [[NeurIPS](http://papers.nips.cc/paper/8706-exploiting-local-and-global-structure-for-point-cloud-semantic-segmentation-with-contextual-point-representations.pdf)] Exploiting Local and Global Structure for Point Cloud Semantic Segmentation with Contextual Point Representations. [[tensorflow](https://github.com/fly519/ELGS)] [__`seg.`__]
- [[NeurIPS](https://arxiv.org/pdf/1907.03739.pdf)] Point-Voxel CNN for Efficient 3D Deep Learning. [__`det.`__ __`seg.`__ __`aut.`__]
- [[NeurIPS](http://papers.nips.cc/paper/8940-pointdan-a-multi-scale-3d-domain-adaption-network-for-point-cloud-representation.pdf)] PointDAN: A Multi-Scale 3D Domain Adaption Network for Point Cloud Representation. [[code](https://github.com/canqin001/PointDAN)] [__`cls.`__ __`oth.`__]
-
- [[ICLR](https://openreview.net/forum?id=SJeXSo09FQ)] Learning Localized Generative Models for 3D Point Clouds via Graph Convolution. [__`oth.`__]
-
- [[ICMLW](https://arxiv.org/abs/1905.07290)] LiDAR Sensor modeling and Data augmentation with GANs for Autonomous driving. [__`det.`__ __`oth.`__ __`aut.`__]
-
- [[AAAI](https://arxiv.org/abs/1811.11731)] CAPNet: Continuous Approximation Projection For 3D Point Cloud Reconstruction Using 2D Supervision. [[code](https://github.com/val-iisc/capnet)] [__`rec.`__]
- [[AAAI](https://arxiv.org/abs/1811.02565)] Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network. [[tensorflow](https://github.com/liuxinhai/Point2Sequence)] [__`cls.`__ __`seg.`__]
- [[AAAI](https://par.nsf.gov/biblio/10086163)] Point Cloud Processing via Recurrent Set Encoding. [__`cls.`__]
- [[AAAI](https://arxiv.org/abs/1812.00333)] PVRNet: Point-View Relation Neural Network for 3D Shape Recognition. [[pytorch](https://github.com/Hxyou/PVRNet)] [__`cls.`__ __`rel.`__]
- [[AAAI](http://gaoyue.org/paper/HGNN.pdf)] Hypergraph Neural Networks. [[pytorch](https://github.com/iMoonLab/HGNN)] [__`cls.`__]
-
- [[TOG](https://arxiv.org/abs/1801.07829)] Dynamic Graph CNN for Learning on Point Clouds. [[tensorflow](https://github.com/WangYueFt/dgcnn)][[pytorch](https://github.com/WangYueFt/dgcnn)] [__`cls.`__ __`seg.`__] :fire: :star:
- [[TOG](https://arxiv.org/pdf/1903.10170.pdf)] LOGAN: Unpaired Shape Transform in Latent Overcomplete Space. [[tensorflow](https://github.com/kangxue/LOGAN)] [__`oth.`__]
- [[SIGGRAPH Asia](https://arxiv.org/abs/1908.00575v1)] StructureNet: Hierarchical Graph Networks for 3D Shape Generation. [__`seg.`__ __`oth.`__]
-
- [[MM](https://dl.acm.org/citation.cfm?id=3343031.3351009)] MMJN: Multi-Modal Joint Networks for 3D Shape Recognition. [__`cls.`__ __`rel.`__]
- [[MM](https://dl.acm.org/citation.cfm?id=3351061)] 3D Point Cloud Geometry Compression on Deep Learning. [__`oth.`__]
- [[MM](https://dl.acm.org/citation.cfm?id=3351042)] SRINet: Learning Strictly Rotation-Invariant Representations for Point Cloud Classification and Segmentation. [[tensorflow](https://github.com/tasx0823/SRINet)] [__`cls.`__ __`seg.`__]
- [[MM](https://dl.acm.org/citation.cfm?id=3350960)] L2G Auto-encoder: Understanding Point Clouds by Local-to-Global Reconstruction with Hierarchical Self-Attention. [__`cls.`__ __`rel.`__]
- [[MM](https://dl.acm.org/citation.cfm?id=3351076)] Ground-Aware Point Cloud Semantic Segmentation for Autonomous Driving. [[code](https://github.com/Jaiy/Ground-aware-Seg)] [__`seg.`__ __`aut.`__]
-
- [[ICME](https://arxiv.org/abs/1908.08996)] Justlookup: One Millisecond Deep Feature Extraction for Point Clouds By Lookup Tables. [__`cls.`__ __`rel.`__]
-
- [[ICASSP](https://arxiv.org/abs/1904.04427)] 3D Point Cloud Denoising via Deep Neural Network based Local Surface Estimation. [[code](https://github.com/chaojingduan/Neural-Projection)] [__`oth.`__]
-
- [[BMVC](https://arxiv.org/abs/1907.06371)] Mitigating the Hubness Problem for Zero-Shot Learning of 3D Objects. [__`cls.`__]
-
- [[ICRA](https://arxiv.org/abs/1904.00319)] Discrete Rotation Equivariance for Point Cloud Recognition. [[pytorch](https://github.com/lijx10/rot-equ-net)] [__`cls.`__]
- [[ICRA](https://arxiv.org/abs/1809.08495)] SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud. [[tensorflow](https://github.com/xuanyuzhou98/SqueezeSegV2)] [__`seg.`__ __`aut.`__]
- [[ICRA](https://www.ais.uni-bonn.de/papers/ICRA_2019_Razlaw.pdf)] Detection and Tracking of Small Objects in Sparse 3D Laser Range Data. [__`det.`__ __`tra.`__ __`aut.`__]
- [[ICRA](https://arxiv.org/abs/1905.02553)] Oriented Point Sampling for Plane Detection in Unorganized Point Clouds. [__`det.`__ __`seg.`__]
- [[ICRA](https://ras.papercept.net/conferences/conferences/ICRA19/program/ICRA19_ContentListWeb_1.html)] Point Cloud Compression for 3D LiDAR Sensor Using Recurrent Neural Network with Residual Blocks. [[pytorch](https://github.com/ChenxiTU/Point-cloud-compression-by-RNN)] [__`oth.`__]
- [[ICRA](https://arxiv.org/abs/1809.06065)] Focal Loss in 3D Object Detection. [[code](https://github.com/pyun-ram/FL3D)] [__`det.`__ __`aut.`__]
- [[ICRA](https://arxiv.org/abs/1809.06267)] PointNetGPD: Detecting Grasp Configurations from Point Sets. [[pytorch](https://github.com/lianghongzhuo/PointNetGPD)] [__`det.`__ __`seg.`__]
- [[ICRA](https://arxiv.org/abs/1904.09742)] 2D3D-MatchNet: Learning to Match Keypoints across 2D Image and 3D Point Cloud. [__`oth.`__]
- [[ICRA](https://ras.papercept.net/conferences/conferences/ICRA19/program/ICRA19_ContentListWeb_2.html)] Speeding up Iterative Closest Point Using Stochastic Gradient Descent. [__`oth.`__]
- [[ICRA](https://ras.papercept.net/conferences/conferences/ICRA19/program/ICRA19_ContentListWeb_2.html)] Uncertainty Estimation for Projecting Lidar Points Onto Camera Images for Moving Platforms. [__`oth.`__]
- [[ICRA](https://ras.papercept.net/conferences/conferences/ICRA19/program/ICRA19_ContentListWeb_2.html)] SEG-VoxelNet for 3D Vehicle Detection from RGB and LiDAR Data. [__`det.`__ __`aut.`__]
- [[ICRA](https://arxiv.org/abs/1903.06405v1)] BLVD: Building A Large-scale 5D Semantics Benchmark for Autonomous Driving. [[project](https://github.com/VCCIV/BLVD)] [__`dat.`__ __`det.`__ __`tra.`__ __`aut.`__ __`oth.`__]
- [[ICRA](https://ras.papercept.net/conferences/conferences/ICRA19/program/ICRA19_ContentListWeb_2.html)] A Fast and Robust 3D Person Detector and Posture Estimator for Mobile Robotic Applications. [__`det.`__]
- [[ICRA](https://arpg.colorado.edu/papers/hmrf_icp.pdf)] Robust low-overlap 3-D point cloud registration for outlier rejection. [[matlab](https://github.com/JStech/ICP)] [__`reg.`__]
- [[ICRA](https://ras.papercept.net/conferences/conferences/ICRA19/program/ICRA19_ContentListWeb_3.html)] Robust 3D Object Classification by Combining Point Pair Features and Graph Convolution. [__`cls.`__ __`seg.`__]
- [[ICRA](https://ras.papercept.net/conferences/conferences/ICRA19/program/ICRA19_ContentListWeb_3.html)] Hierarchical Depthwise Graph Convolutional Neural Network for 3D Semantic Segmentation of Point Clouds. [__`seg.`__]
- [[ICRA](https://ras.papercept.net/conferences/conferences/ICRA19/program/ICRA19_ContentListWeb_3.html)] Robust Generalized Point Set Registration Using Inhomogeneous Hybrid Mixture Models Via Expectation. [__`reg.`__]
- [[ICRA](https://arxiv.org/abs/1902.07511)] Dense 3D Visual Mapping via Semantic Simplification. [__`oth.`__]
- [[ICRA](https://arxiv.org/abs/1904.01649)] MVX-Net: Multimodal VoxelNet for 3D Object Detection. [__`det.`__ __`aut.`__]
- [[ICRA](https://export.arxiv.org/abs/1810.01470)] CELLO-3D: Estimating the Covariance of ICP in the Real World. [__`reg.`__]
-
- [[IROS](https://www.researchgate.net/publication/334720713_EPN_Edge-Aware_PointNet_for_Object_Recognition_from_Multi-View_25D_Point_Clouds)] EPN: Edge-Aware PointNet for Object Recognition from Multi-View 2.5D Point Clouds. [[tensorflow](https://github.com/Merium88/Edge-Aware-PointNet)] [__`cls.`__ __`det.`__]
- [[IROS](https://arxiv.org/pdf/1904.13030.pdf)] SeqLPD: Sequence Matching Enhanced Loop-Closure Detection Based on Large-Scale Point Cloud Description for Self-Driving Vehicles. [__`oth.`__] [__`aut.`__]
- [[IROS](https://arxiv.org/pdf/1909.01643v1.pdf)] PASS3D: Precise and Accelerated Semantic Segmentation for 3D Point Cloud. [__`seg.`__ __`aut.`__]
-
- [[IV](https://arxiv.org/abs/1906.10964)] End-to-End 3D-PointCloud Semantic Segmentation for Autonomous Driving. [__`seg.`__] [__`aut.`__]
-
- [[Eurographics Workshop](https://arxiv.org/abs/1904.02375)] Generalizing Discrete Convolutions for Unstructured Point Clouds. [[pytorch](https://github.com/aboulch/ConvPoint)] [__`cls.`__ __`seg.`__]
-
- [[WACV](https://arxiv.org/abs/1811.02191)] 3DCapsule: Extending the Capsule Architecture to Classify 3D Point Clouds. [__`cls.`__]
-
- [[3DV](https://arxiv.org/pdf/1908.06297.pdf)] Rotation Invariant Convolutions for 3D Point Clouds Deep Learning. [[project](https://hkust-vgd.github.io/riconv/)] [__`cls.`__ __`seg.`__]
- [[3DV](https://arxiv.org/abs/1906.11555)] Effective Rotation-invariant Point CNN with Spherical Harmonics kernels. [[tensorflow](https://github.com/adrienPoulenard/SPHnet)] [__`cls.`__ __`seg.`__ __`oth.`__]
-
- [[TVCG](https://arxiv.org/pdf/1907.13538.pdf)] LassoNet: Deep Lasso-Selection of 3D Point Clouds. [[project](https://lassonet.github.io/)] [__`oth.`__]
-
- [[arXiv](https://arxiv.org/abs/1901.02532)] Fast 3D Line Segment Detection From Unorganized Point Cloud. [__`det.`__]
- [[arXiv](https://arxiv.org/abs/1812.01687)] Point-Cloud Saliency Maps. [[tensorflow](https://github.com/tianzheng4/PointCloud-Saliency-Maps)] [__`cls.`__ __`oth.`__]
- [[arXiv](https://export.arxiv.org/abs/1901.03006)] Extending Adversarial Attacks and Defenses to Deep 3D Point Cloud Classifiers. [[code](https://github.com/Daniel-Liu-c0deb0t/3D-Neural-Network-Adversarial-Attacks)] [__`oth.`__]
- [[arxiv](https://arxiv.org/abs/1901.08396)] Context Prediction for Unsupervised Deep Learning on Point Clouds. [__`cls.`__ __`seg.`__]
- [[arXiv](http://export.arxiv.org/abs/1901.09280)] Points2Pix: 3D Point-Cloud to Image Translation using conditional Generative Adversarial Networks. [__`oth.`__]
- [[arXiv](http://export.arxiv.org/abs/1901.09394)] NeuralSampler: Euclidean Point Cloud Auto-Encoder and Sampler. [__`cls.`__ __`oth.`__]
- [[arXiv](https://arxiv.org/abs/1902.05247)] 3D Graph Embedding Learning with a Structure-aware Loss Function for Point Cloud Semantic Instance Segmentation. [__`seg.`__]
- [[arXiv](https://arxiv.org/abs/1902.10272)] Zero-shot Learning of 3D Point Cloud Objects. [[code](https://github.com/alichr/Zero-shot-Learning-of-3D-Point-Cloud-Objects)] [__`cls.`__]
- [[arXiv](https://arxiv.org/abs/1903.09847)] Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud. [__`det.`__ __`aut.`__]
- [[arXiv](https://arxiv.org/abs/1903.01695)] Real-time Multiple People Hand Localization in 4D Point Clouds. [__`det.`__ __`oth.`__]
- [[arXiv](https://arxiv.org/abs/1903.02858)] Variational Graph Methods for Efficient Point Cloud Sparsification. [__`oth.`__]
- [[arXiv](https://arxiv.org/abs/1903.05807)] Neural Style Transfer for Point Clouds. [__`oth.`__]
- [[arXiv](https://arxiv.org/abs/1903.07918)] OREOS: Oriented Recognition of 3D Point Clouds in Outdoor Scenarios. [__`pos.`__ __`oth.`__]
- [[arXiv](https://arxiv.org/abs/1903.10750)] FVNet: 3D Front-View Proposal Generation for Real-Time Object Detection from Point Clouds. [[code](https://github.com/LordLiang/FVNet)] [__`det.`__ __`aut.`__]
- [[arXiv](https://arxiv.org/abs/1904.00069)] Unpaired Point Cloud Completion on Real Scans using Adversarial Training. [__`oth.`__]
- [[arXiv](https://arxiv.org/abs/1904.00230)] MortonNet: Self-Supervised Learning of Local Features in 3D Point Clouds. [__`cls.`__ __`seg.`__]
- [[arXiv](https://arxiv.org/abs/1904.00817)] DeepPoint3D: Learning Discriminative Local Descriptors using Deep Metric Learning on 3D Point Clouds. [__`cls.`__ __`rel.`__ __`oth.`__]
- [[arXiv](https://arxiv.org/abs/1904.07537)] Complexer-YOLO: Real-Time 3D Object Detection and Tracking on Semantic Point Clouds. [[pytorch](https://github.com/AI-liu/Complex-YOLO)] [__`det.`__ __`tra.`__ __`aut.`__] :fire:
- [[arXiv](https://arxiv.org/abs/1904.10795)] Graph-based Inpainting for 3D Dynamic Point Clouds. [__`oth.`__]
- [[arXiv](https://arxiv.org/abs/1903.11027)] nuScenes: A multimodal dataset for autonomous driving. [[link](https://www.nuscenes.org/overview)] [__`dat.`__ __`det.`__ __`tra.`__ __`aut.`__]
- [[arXiv](https://arxiv.org/abs/1901.08373)] 3D Backbone Network for 3D Object Detection. [[code](https://github.com/Benzlxs/tDBN)] [__`det.`__ __`aut.`__]
- [[arXiv](https://arxiv.org/abs/1811.07605v3)] Adversarial Autoencoders for Compact Representations of 3D Point Clouds. [[pytorch](https://github.com/MaciejZamorski/3d-AAE)] [__`rel.`__ __`oth.`__]
- [[arXiv](https://arxiv.org/pdf/1904.10014.pdf)] Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features. [__`cls.`__ __`seg.`__]
- [[arXiv](https://arxiv.org/abs/1905.08705)] GAPNet: Graph Attention based Point Neural Network for Exploiting Local Feature of Point Cloud. [[tensorflow](https://github.com/FrankCAN/GAPNet)] [__`cls.`__ __`seg.`__]
- [[arXiv](https://arxiv.org/abs/1906.01140)] Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds. [[tensorflow](https://github.com/Yang7879/3D-BoNet)] [__`det.`__ __`seg.`__]
- [[arXiv](https://export.arxiv.org/abs/1906.04173)] Differentiable Surface Splatting for Point-based Geometry Processing. [[pytorch](https://github.com/yifita/DSS)] [__`oth.`__]
- [[arXiv](https://arxiv.org/abs/1906.10887)] Spatial Transformer for 3D Points. [__`seg.`__]
- [[arXiv](https://arxiv.org/abs/1907.03739)] Point-Voxel CNN for Efficient 3D Deep Learning. [__`seg.`__ __`det.`__ __`aut.`__]
- [[arXiv](https://arxiv.org/pdf/1907.02545.pdf)] Attentive Context Normalization for Robust Permutation-Equivariant Learning. [__`cls.`__]
- [[arXiv](https://arxiv.org/abs/1906.08240)] Neural Point-Based Graphics. [[project](https://dmitryulyanov.github.io/neural_point_based_graphics)] [__`oth.`__]
- [[arXiv](https://arxiv.org/pdf/1908.02111.pdf)] Point Cloud Super Resolution with Adversarial Residual Graph Networks. [__`oth.`__] [[tensorflow](https://github.com/wuhuikai/PointCloudSuperResolution)]
- [[arXiv](https://arxiv.org/pdf/1908.10209.pdf)] Blended Convolution and Synthesis for Efficient Discrimination of 3D Shapes. [__`cls.`__ __`rel.`__]
- [[arXiv](https://arxiv.org/pdf/1908.11069v1.pdf)] StarNet: Targeted Computation for Object Detection in Point Clouds. [[tensorflow](https://github.com/tensorflow/lingvo)] [__`det.`__]
- [[arXiv](https://arxiv.org/pdf/1903.10168.pdf)] Efficient Tracking Proposals using 2D-3D Siamese Networks on LIDAR. [__`tra.`__]
- [[arXiv](https://arxiv.org/pdf/1905.07650v1.pdf)] SAWNet: A Spatially Aware Deep Neural Network for 3D Point Cloud Processing. [[tensorflow](https://github.com/balwantraikekutte/SAWNet)] [__`cls.`__ __`seg.`__]
- [[arXiv](https://arxiv.org/abs/1907.03670)] Part-A^2 Net: 3D Part-Aware and Aggregation Neural Network for Object Detection from Point Cloud. [__`det.`__ __`aut.`__]
- [[arXiv](https://arxiv.org/pdf/1906.03299.pdf)] PyramNet: Point Cloud Pyramid Attention Network and Graph Embedding Module for Classification and Segmentation. [__`cls.`__ __`seg.`__]
- [[arXiv](https://arxiv.org/pdf/1910.08287.pdf)] PointRNN: Point Recurrent Neural Network for Moving Point Cloud Processing. [[tensorflow](https://github.com/hehefan/PointRNN)] [__`tra.`__ __`oth.`__ __`aut.`__]
- [[arXiv](https://arxiv.org/abs/1907.09798)] PointAtrousGraph: Deep Hierarchical Encoder-Decoder with Point Atrous Convolution for Unorganized 3D Points. [[tensorflow](https://github.com/paul007pl/PointAtrousGraph)] [__`cls.`__ __`seg.`__]
- [[arXiv](https://arxiv.org/pdf/1907.05279.pdf)] Tranquil Clouds: Neural Networks for Learning Temporally Coherent Features in Point Clouds. [__`oth.`__]
- [[arXiv](https://arxiv.org/pdf/1911.09040.pdf)] 3D-Rotation-Equivariant Quaternion Neural Networks. [__`cls.`__ __`rec.`__]
- [[arXiv](https://arxiv.org/pdf/1908.11026.pdf)] Point2SpatialCapsule: Aggregating Features and Spatial Relationships of Local Regions on Point Clouds using Spatial-aware Capsules. [__`cls.`__ __`rel.`__ __`seg.`__]
- [[arXiv](https://arxiv.org/abs/1911.12885)] Geometric Feedback Network for Point Cloud Classification. [__`cls.`__]
- [[arXiv](https://arxiv.org/abs/1912.00202)] Relation Graph Network for 3D Object Detection in Point Clouds. [__`det.`__]
- [[arXiv](https://arxiv.org/pdf/1907.13079.pdf)] Deformable Filter Convolution for Point Cloud Reasoning. [__`seg.`__ __`det.`__ __`aut.`__]
- [[arXiv](https://arxiv.org/pdf/1912.03264.pdf)] PU-GCN: Point Cloud Upsampling via Graph Convolutional Network. [[project](https://sites.google.com/kaust.edu.sa/pugcn)] [__`oth.`__]
- [[arXiv](https://arxiv.org/pdf/1912.02984v1.pdf)] Grid-GCN for Fast and Scalable Point Cloud Learning. [__`seg.`__ __`cls.`__]
- [[arXiv](https://arxiv.org/pdf/1911.10150.pdf)] PointPainting: Sequential Fusion for 3D Object Detection. [__`seg.`__ __`det.`__]
- [[arXiv](https://arxiv.org/pdf/1912.07161.pdf)] Transductive Zero-Shot Learning for 3D Point Cloud Classification. [__`cls.`__]
- [[arXiv](https://arxiv.org/pdf/1912.10644.pdf)] Geometry Sharing Network for 3D Point Cloud Classification and Segmentation. [[pytorch](https://github.com/MingyeXu/GS-Net)] [__`cls.`__ __`seg.`__]
- [[arvix](https://arxiv.org/abs/1912.12033)] Deep Learning for 3D Point Clouds: A Survey. [[code](https://github.com/QingyongHu/SoTA-Point-Cloud)] [__`cls.`__ __`det.`__ __`tra.`__ __`seg.`__]
- [[arXiv](https://arxiv.org/pdf/1912.01800v1.pdf)] Spectral-GANs for High-Resolution 3D Point-cloud Generation. [__`rec.`__ __`oth.`__]
- [[arXiv](https://arxiv.org/pdf/1909.12663.pdf)] Point Attention Network for Semantic Segmentation of 3D Point Clouds. [__`seg.`__]
- [[arXiv](https://arxiv.org/pdf/1909.07137v1.pdf)] PLIN: A Network for Pseudo-LiDAR Point Cloud Interpolation. [__`oth.`__]
- [[arXiv](https://arxiv.org/abs/1904.08159)] 3D Object Recognition with Ensemble Learning --- A Study of Point Cloud-Based Deep Learning Models. [__`cls.`__ __`det.`__]
-
---
## 2020
- [[AAAI](https://arxiv.org/abs/1912.00280)] Morphing and Sampling Network for Dense Point Cloud Completion. [[pytorch](https://github.com/Colin97/MSN-Point-Cloud-Completion)] [__`oth.`__]
- [[AAAI](https://arxiv.org/pdf/1912.05163.pdf)] TANet: Robust 3D Object Detection from Point Clouds with Triple Attention. [[code](https://github.com/happinesslz/TANet)] [__`det.`__ __`aut.`__]
- [[AAAI](https://arxiv.org/abs/1912.10775)] Point2Node: Correlation Learning of Dynamic-Node for Point Cloud Feature Modeling. [__`seg.`__ __`cls.`__]
- [[AAAI](https://arxiv.org/abs/1811.09361)] PRIN: Pointwise Rotation-Invariant Network. [__`seg.`__ __`cls.`__]
- [[AAAI](https://www.aaai.org/Papers/AAAI/2020GB/AAAI-WuW.2180.pdf)] SK-Net: Deep Learning on Point Cloud via End-to-end Discovery of Spatial Keypoints. [__`oth`__]
- [[AAAI](https://arxiv.org/pdf/1912.09654.pdf)] JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds. [[tensorflow](https://github.com/dlinzhao/JSNet)][__`seg.`__]
- [[AAAI](https://arxiv.org/pdf/2003.00529.pdf)] ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection. [__`det.`__]
- [[AAAI](https://arxiv.org/abs/2004.09411)] Shape-Oriented Convolution Neural Network for Point Cloud Analysis. [__`cls.`__]
-
- [[CVPR](https://arxiv.org/pdf/1911.11236.pdf)] RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds. [[tensorflow](https://github.com/QingyongHu/RandLA-Net)] [__`seg.`__] :fire:
- [[CVPR](https://arxiv.org/abs/2001.05119)] Learning multiview 3D point cloud registration. [[code](https://github.com/zgojcic/3D_multiview_reg)] [__`reg.`__]
- [[CVPR](https://arxiv.org/pdf/2003.00410.pdf)] PF-Net: Point Fractal Network for 3D Point Cloud Completion. [[pytorch](https://github.com/zztianzz/PF-Net-Point-Fractal-Network.git)] [__`oth.`__]
- [[CVPR](https://arxiv.org/abs/2001.10692)] ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votes. [__`det.`__]
- [[CVPR](https://arxiv.org/pdf/2003.06233.pdf)] Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation. [[pytorch](https://github.com/jzhzhang/FusionAwareConv)] [__`seg.`__]
- [[CVPR](https://arxiv.org/pdf/1903.10297.pdf)] AdaCoSeg: Adaptive Shape Co-Segmentation with Group Consistency Loss. [__`seg.`__]
- [[CVPR](http://www4.comp.polyu.edu.hk/~cslzhang/paper/SA-SSD.pdf)] SA-SSD: Structure Aware Single-Stage 3D Object Detection from Point Cloud. [[pytorch](https://github.com/skyhehe123/SA-SSD)] [__`det.`__] :fire:
- [[CVPR](https://arxiv.org/pdf/2002.10876.pdf)] PointAugment: an Auto-Augmentation Framework for Point Cloud Classification. [[code](https://github.com/liruihui/PointAugment/)] [__`classification.`__]
- [[CVPR](https://arxiv.org/pdf/2003.01251.pdf)] Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud. [[tensorflow](https://github.com/WeijingShi/Point-GNN)][__`det.`__] :fire:
- [[CVPR](https://arxiv.org/pdf/2003.13035.pdf)] Multi-Path Region Mining For Weakly Supervised 3D Semantic Segmentation on Point Clouds. [__`seg.`__]
- [[CVPR](https://arxiv.org/pdf/2003.12971.pdf)] Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds. [[pytorch](https://github.com/raoyongming/PointGLR)][__`oth.`__]
- [[CVPR](https://arxiv.org/pdf/2003.13326.pdf)] PointGMM: a Neural GMM Network for Point Clouds. [[code](https://github.com/amirhertz/pointgmm)][__`cls.`__]
- [[CVPR](https://arxiv.org/pdf/2003.13479.pdf)] RPM-Net: Robust Point Matching using Learned Features. [[code](https://github.com/yewzijian/RPMNet)] [__`seg.`__]
- [[CVPR](https://arxiv.org/pdf/2003.01661.pdf)] Unsupervised Learning of Intrinsic Structural Representation Points. [[pytorch](https://github.com/NolenChen/3DStructurePoints)][__`oth.`__]
- [[CVPR](https://arxiv.org/pdf/2003.14032.pdf)] PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation. [[pytorch](https://github.com/edwardzhou130/PolarSeg)] [__`seg.`__]
- [[CVPR](https://arxiv.org/pdf/2003.13867.pdf)] 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation. [__`seg.`__]
- [[CVPR](https://arxiv.org/pdf/2004.01170.pdf)] DOPS: Learning to Detect 3D Objects and Predict their 3D Shapes. [__`det.`__]
- [[CVPR](https://arxiv.org/pdf/2003.06537.pdf)] OccuSeg: Occupancy-aware 3D Instance Segmentation. [__`seg.`__]
- [[CVPR](https://arxiv.org/pdf/2003.06754.pdf)] MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps. [__`oth.`__]
- [[CVPR](https://arxiv.org/pdf/2003.05593.pdf)] Learning to Segment 3D Point Clouds in 2D Image Space. [[pytorch](https://github.com/Zhang-VISLab/Learning-to-Segment-3D-Point-Clouds-in-2D-Image-Space)] [__`seg`__]
- [[CVPR](https://arxiv.org/pdf/2003.03164.pdf)] D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features. [__`cls`__]
- [[CVPR](https://arxiv.org/pdf/2003.00492.pdf)] PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling. [__`cls.`__]
- [[CVPR](https://arxiv.org/pdf/2004.00543.pdf)] Physically Realizable Adversarial Examples for LiDAR Object Detection. [__`det.`__]
- [[CVPR](https://arxiv.org/pdf/2003.00186.pdf)] HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection. [__`det`__]
- [[CVPR](https://arxiv.org/abs/2004.01389)] LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention. [[code](https://github.com/yinjunbo/3DVID)][__`det.`__]
- [[CVPR](https://arxiv.org/pdf/2004.01658.pdf)] PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation. [__`seg.`__]
- [[CVPR](https://arxiv.org/abs/2004.02869)] DualSDF: Semantic Shape Manipulation using a Two-Level Representation. [[code](https://github.com/zekunhao1995/DualSDF)][__`seg`__]
- [[CVPR](https://arxiv.org/abs/2004.03572)] Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation. [[pytorch](https://github.com/zju3dv/disprcnn)][__`det.`__]
- [[CVPR](https://arxiv.org/abs/2004.03080)] End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection. [[code](https://github.com/mileyan/pseudo-LiDAR_e2e)] [__`det.`__]
- [[CVPR](https://arxiv.org/abs/2004.03327)] Cascaded Refinement Network for Point Cloud Completion. [[code](https://github.com/xiaogangw/cascaded-point-completion)][__`completion`__]
- [[CVPR](https://arxiv.org/abs/2004.05679)] MLCVNet: Multi-Level Context VoteNet for 3D Object Detection. [[code](https://github.com/NUAAXQ/MLCVNet)][__`det.`__]
- [[CVPR](https://arxiv.org/abs/2004.03967)] Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions. [__`oth.`__]
- [[CVPR](https://arxiv.org/abs/2004.09305)] Joint Spatial-Temporal Optimization for Stereo 3D Object Tracking. [__`track.`__]
- [[CVPR](https://arxiv.org/abs/1911.11098)] StructEdit: Learning Structural Shape Variations. [[project](https://github.com/daerduoCarey/structedit)] [__`rec.`__]
- [[CVPR](https://hal.inria.fr/hal-02541349/document)] Connect-and-Slice: an hybrid approach for reconstructing 3D objects. [__`reconstruction.`__]
- [[CVPR](https://arxiv.org/abs/1912.00195v1)] SGAS: Sequential Greedy Architecture Search. [[pytorch](https://github.com/lightaime/sgas)] [__'cls.'__]
- [[CVPR oral](https://arxiv.org/abs/2004.11540)] Deep Global Registration. [__'reg.'__]
- [[CVPR](https://arxiv.org/pdf/2002.10187.pdf)] 3DSSD: Point-based 3D Single Stage Object Detector. [__`det`__]
- [[CVPR](http://geometry.cs.ucl.ac.uk/projects/2020/deepleanpn/paper_docs/GoingDeeperWithPointNetworksLeKokkinosMitra.pdf)] Going Deeper with Point Networks. [[pytorch](https://github.com/erictuanle/GoingDeeperwPointNetworks)][__'cls.'__]
- [[CVPR](http://www-sop.inria.fr/members/Florent.Lafarge/)] Connect-and-Slice: an hybrid approach for reconstructing 3D objects. [__`reconstruction`__]
- [[CVPR](https://arxiv.org/abs/2005.01014)] Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondences. [__`registration`__]
- [[CVPR](https://arxiv.org/abs/2005.01939)] From Image Collections to Point Clouds with Self-supervised Shape and Pose Networks. [[tensorflow](https://github.com/val-iisc/ssl_3d_recon)][__'image-to-point cloud.'__]
- [[CVPR](https://arxiv.org/abs/1911.10150)] PointPainting: Sequential Fusion for 3D Object Detection. [__`detection`__]
- [[CVPR](https://arxiv.org/abs/1911.12676)] xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation. [__`Segmentation`__]
- [[CVPR](https://arxiv.org/pdf/2005.05125.pdf)] FroDO: From Detections to 3D Objects. [__`detection`__]
- [[CVPR oral](https://arxiv.org/abs/2005.07178)] OctSqueeze: Octree-Structured Entropy Model for LiDAR Compression. [__`Compression`__]
- [[CVPR](https://arxiv.org/abs/2005.08139)] Train in Germany, Test in The USA: Making 3D Object Detectors Generalize. [[code](https://github.com/cxy1997/3D_adapt_auto_driving)][__`detection`__]
- [[CVPR oral](https://arxiv.org/abs/2005.08144)] High-dimensional Convolutional Networks for Geometric Pattern Recognition. [[code](https://github.com/chrischoy/HighDimConvNets)][__`Recognition`__]
- [[CVPR oral](https://arxiv.org/abs/2005.13888)] P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds. [[pytorch](https://github.com/HaozheQi/P2B)][__`Tracking`__]
- [[CVPR](https://arxiv.org/pdf/2006.04356.pdf)] Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection. [__`detection`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2020/papers/Hou_RevealNet_Seeing_Behind_Objects_in_RGB-D_Scans_CVPR_2020_paper.pdf)] RevealNet: Seeing Behind Objects in RGB-D Scans. [__`Completion`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2020/papers/Chen_A_Hierarchical_Graph_Network_for_3D_Object_Detection_on_Point_CVPR_2020_paper.pdf)] A Hierarchical Graph Network for 3D Object Detection on Point Clouds. [__`Detection`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2020/papers/Ahmed_Density-Based_Clustering_for_3D_Object_Detection_in_Point_Clouds_CVPR_2020_paper.pdf)] Density Based Clustering for 3D Object Detection in Point Clouds. [__`Detection`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2020/papers/Zhou_Joint_3D_Instance_Segmentation_and_Object_Detection_for_Autonomous_Driving_CVPR_2020_paper.pdf)] Joint 3D Instance Segmentation and Object Detection for Autonomous Driving. [__`Detection`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2020/papers/Fujiwara_Neural_Implicit_Embedding_for_Point_Cloud_Analysis_CVPR_2020_paper.pdf)] Neural Implicit Embedding for Point Cloud Analysis. [__`Analysis`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2020/papers/Jiang_End-to-End_3D_Point_Cloud_Instance_Segmentation_Without_Detection_CVPR_2020_paper.pdf)] End-to-End 3D Point Cloud Instance Segmentation Without Detection. [__`Segmentation`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2020/papers/Nezhadarya_Adaptive_Hierarchical_Down-Sampling_for_Point_Cloud_Classification_CVPR_2020_paper.pdf)] Adaptive Hierarchical Down-Sampling for Point Cloud Classification. [__`Classification`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2020/papers/Zhou_Geometry_and_Learning_Co-Supported_Normal_Estimation_for_Unstructured_Point_Cloud_CVPR_2020_paper.pdf)] Geometry and Learning Co-Supported Normal Estimation for Unstructured Point Cloud. [__`Normal`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2020/papers/Xu_Weakly_Supervised_Semantic_Point_Cloud_Segmentation_Towards_10x_Fewer_Labels_CVPR_2020_paper.pdf)] Weakly Supervised Semantic Point Cloud Segmentation: Towards 10x Fewer Labels. [__`Segmentation`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2020/papers/Lei_SegGCN_Efficient_3D_Point_Cloud_Segmentation_With_Fuzzy_Spherical_Kernel_CVPR_2020_paper.pdf)] SegGCN: Efficient 3D Point Cloud Segmentation With Fuzzy Spherical Kernel. [__`Segmentation`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2020/papers/Zhou_LG-GAN_Label_Guided_Adversarial_Network_for_Flexible_Targeted_Attack_of_CVPR_2020_paper.pdf)] LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud Based Deep Networks. [__`Attack`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2020/papers/Lang_SampleNet_Differentiable_Point_Cloud_Sampling_CVPR_2020_paper.pdf)] SampleNet: Differentiable Point Cloud Sampling. [__`Sampling`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2020/papers/Wang_Sequential_3D_Human_Pose_and_Shape_Estimation_From_Point_Clouds_CVPR_2020_paper.pdf)] Sequential 3D Human Pose and Shape Estimation From Point Clouds. [__`Pose`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2020/papers/Min_An_Efficient_PointLSTM_for_Point_Clouds_Based_Gesture_Recognition_CVPR_2020_paper.pdf)] An Efficient PointLSTM for Point Clouds Based Gesture Recognition. [__`Recognition`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2020/papers/Xu_Grid-GCN_for_Fast_and_Scalable_Point_Cloud_Learning_CVPR_2020_paper.pdf)] Grid-GCN for Fast and Scalable Point Cloud Learning. [__`other`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2020/papers/Shi_SpSequenceNet_Semantic_Segmentation_Network_on_4D_Point_Clouds_CVPR_2020_paper.pdf)] SpSequenceNet: Semantic Segmentation Network on 4D Point Clouds. [__`Segmentation`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2020/papers/Wen_Point_Cloud_Completion_by_Skip-Attention_Network_With_Hierarchical_Folding_CVPR_2020_paper.pdf)] Point Cloud Completion by Skip-attention Network with Hierarchical Folding. [__`Completion`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2020/papers/Li_End-to-End_Learning_Local_Multi-View_Descriptors_for_3D_Point_Clouds_CVPR_2020_paper.pdf)] End-to-End Learning Local Multi-View Descriptors for 3D Point Clouds. [__`Description`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2020/papers/Lin_Convolution_in_the_Cloud_Learning_Deformable_Kernels_in_3D_Graph_CVPR_2020_paper.pdf)] Convolution in the Cloud: Learning Deformable Kernels in 3D Graph Convolution Networks for Point Cloud Analysis. [__`other`__]
- [[CVPR](http://openaccess.thecvf.com/content_CVPR_2020/papers/Zhao_On_Isometry_Robustness_of_Deep_3D_Point_Cloud_Models_Under_CVPR_2020_paper.pdf)] On Isometry Robustness of Deep 3D Point Cloud Models Under Adversarial Attacks. [__`other`__]
- [[CVPR](https://openaccess.thecvf.com/content_CVPR_2020/html/Pais_3DRegNet_A_Deep_Neural_Network_for_3D_Point_Registration_CVPR_2020_paper.html)] 3DRegNet: A Deep Neural Network for 3D Point Registration. [__`reg.`__]
- [[CVPR](https://openaccess.thecvf.com/content_CVPR_2020/html/Iglesias_Global_Optimality_for_Point_Set_Registration_Using_Semidefinite_Programming_CVPR_2020_paper.html)] Global Optimality for Point Set Registration Using Semidefinite Programming. [__`reg.`__]
- [[CVPRW](https://arxiv.org/abs/2006.12671)] AFDet: Anchor Free One Stage 3D Object Detection. [__`Detection.`__]
-
- [[ECCV]] EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection. [[code](https://github.com/happinesslz/EPNet)][__`Detection`__]
- [[ECCV](https://arxiv.org/pdf/2004.12636.pdf)] 3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection. [[code](https://github.com/rasd3/3D-CVF)][__`Detection`__]
- [[ECCV](https://arxiv.org/abs/2006.03761)] GRNet: Gridding Residual Network for Dense Point Cloud Completion. [[code](https://github.com/hzxie/GRNet)][__`Completion`__]
- [[ECCV](https://arxiv.org/abs/2007.01294)] A Closer Look at Local Aggregation Operators in Point Cloud Analysis. [[pytorch/tensorflow](https://github.com/zeliu98/CloserLook3D)][__`Analysis.`__]
- [[ECCV](https://arxiv.org/abs/2004.02693)] Finding Your (3D) Center: 3D Object Detection Using a Learned Loss. [__`Detection.`__]
- [[ECCV](https://arxiv.org/pdf/2006.05682.pdf)] H3DNet: 3D Object Detection Using Hybrid Geometric Primitives. [[pytorch](https://github.com/zaiweizhang/H3DNet)][__`Detection.`__]
- [[ECCV](https://arxiv.org/pdf/1912.12098.pdf)] Quaternion Equivariant Capsule Networks for 3D Point Clouds. [__`Classification`__]
- [[ECCV](https://arxiv.org/abs/2004.01661)] Intrinsic Point Cloud Interpolation via Dual Latent Space Navigation. [__`Interpolation`__]
- [[ECCV](https://arxiv.org/abs/1911.12408)] PointPWC-Net: Cost Volume on Point Clouds for (Self-)Supervised Scene Flow Estimation. [__`Flow`__]
- [[ECCV](https://arxiv.org/pdf/2006.05682.pdf)] H3DNet: 3D Object Detection Using Hybrid Geometric Primitives. [[pytorch](https://github.com/zaiweizhang/H3DNet)][__`Detection.`__]
- [[ECCV](https://arxiv.org/abs/2003.12181)] ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds. [__`Fitting`__]
- [[ECCV](https://arxiv.org/abs/2003.13834)] Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions. [[code](https://github.com/matheusgadelha/PointCloudLearningACD)][__`Learning`__]
- [[ECCV](https://arxiv.org/abs/2004.11784)] DPDist : Comparing Point Clouds Using Deep Point Cloud Distance. [__`Comparing`__]
- [[ECCV](https://arxiv.org/abs/2004.02774)] SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds. [[code](https://github.com/xinge008/SSN)][__`Detection`__]
- [[ECCV](https://arxiv.org/abs/2002.10277)] PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsampling. [__`Upsampling`__]
- [[ECCV](https://arxiv.org/abs/1912.00461)] AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds. [__`Perturbations`__]
- [[ECCV](https://arxiv.org/abs/2007.02578)] Learning Graph-Convolutional Representations for Point Cloud Denoising. [__`Denoising`__]
- [[ECCV](https://arxiv.org/pdf/2007.02374.pdf)] Detail Preserved Point Cloud Completion via Separated Feature Aggregation. [[tensorflow](https://github.com/XLechter/Detail-Preserved-Point-Cloud-Completion-via-SFA)][__`Completion`__]
- [[ECCV](https://arxiv.org/pdf/2007.05361.pdf)] Progressive Point Cloud Deconvolution Generation Network. [[code](https://github.com/fpthink/PDGN)][__`Generation`__]
- [[ECCV](https://arxiv.org/pdf/2007.06888.pdf)] JSENet: Joint Semantic Segmentation and Edge Detection Network for 3D Point Clouds. [[code](https://github.com/hzykent/JSENet)][__`Segmentation`__]
- [[ECCV](https://arxiv.org/pdf/2007.08454.pdf)] Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation. [[pytorch](https://github.com/mentian/object-deformnet)][__`Pose`__]
- [[ECCV](https://arxiv.org/pdf/2007.09594.pdf)] Mapping in a cycle: Sinkhorn regularized unsupervised learning for point cloud shapes. [__`Correspondence`__]
- [[ECCV](https://arxiv.org/pdf/2007.10323.pdf)] Pillar-based Object Detection for Autonomous Driving. [[tensorflow](https://github.com/WangYueFt/pillar-od)][__`Detection`__]
- [[ECCV](https://arxiv.org/pdf/2007.09217.pdf)] DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF Relocalization. [[pytorch](https://vision.in.tum.de/research/vslam/dh3d)][__`Localization`__]
- [[ECCV](https://arxiv.org/pdf/2007.09267.pdf)] Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance. [__`Meshing`__]
- [[ECCV](https://arxiv.org/pdf/2007.10170.pdf)] Discrete Point Flow Networks for Efficient Point Cloud Generation. [__`Generation`__]
- [[ECCV](https://arxiv.org/pdf/2007.10985.pdf)] PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding. [__`Unsupervised,Understanding`__]
- [[ECCV](https://arxiv.org/pdf/2007.10453.pdf)] Points2Surf: Learning Implicit Surfaces from Point Cloud Patches. [__`Surfaces`__]
- [[ECCV](https://arxiv.org/pdf/2007.11965.pdf)] CAD-Deform: Deformable Fitting of CAD Models to 3D Scans. [__`Fitting`__]
- [[ECCV](https://arxiv.org/pdf/2007.11901.pdf)] Weakly Supervised 3D Object Detection from Lidar Point Cloud. [__`Detection`__]
- [[ECCV](https://arxiv.org/pdf/2007.13344.pdf)] Self-Prediction for Joint Instance and Semantic Segmentation of Point Clouds. [__`Segmentation`__]
- [[ECCV](https://arxiv.org/pdf/2007.13138.pdf)] Virtual Multi-view Fusion for 3D Semantic Segmentation. [__`Segmentation`__]
- [[ECCV](https://arxiv.org/pdf/2007.16100.pdf)] Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution. [__`Segmentation`__]
- [[ECCV](https://arxiv.org/pdf/2003.07717.pdf)] Multimodal Shape Completion via Conditional Generative Adversarial Networks. [[pytorch](https://github.com/ChrisWu1997/Multimodal-Shape-Completion)][__`Completion`__]
- [[ECCV](https://arxiv.org/pdf/2008.06374.pdf)] PointMixup: Augmentation for Point Clouds. [[code](https://github.com/yunlu-chen/PointMixup/)][__`Classification`__]
- [[ECCV](http://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123560222.pdf)] SPOT: Selective Point Cloud Voting for Better Proposal in Point Cloud Object Detection. [__`Detection`__]
- [[ECCV](http://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123650460.pdf)] Rotation-robust Intersection over Union for 3D Object Detection. [__`3D IOU`__]
- [[ECCV](http://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123480069.pdf)] SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification. [__`Classification, Completion`__]
- [[ECCV](http://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123720494.pdf)] Efficient Outdoor 3D Point Cloud Semantic Segmentation for Critical Road Objects and Distributed Contexts. [__`Segmentation`__]
- [[ECCV](http://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123550596.pdf)] CN: Channel Normalization For Point Cloud Recognition. [__`Recognition`__]
- [[ECCV](http://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123500273.pdf)] Weakly-supervised 3D Shape Completion in the Wild. [__`Completion`__]
- [[ECCV](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123690630.pdf)] Deep FusionNet for Point Cloud Semantic Segmentation. [[code](https://github.com/feihuzhang/LiDARSeg)][__`Segmentation`__]
- [[ECCV](https://arxiv.org/abs/2004.01803)] SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation. [[code](https://github.com/chenfengxu714/SqueezeSegV3)][__`seg.`__]
- [[ECCV](https://arxiv.org/abs/2007.08556)] InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling. [__`Detection`__]
- [[[ECCV](https://link.springer.com/chapter/10.1007/978-3-030-58586-0_23)] Iterative Distance-Aware Similarity Matrix Convolution with Mutual-Supervised Point Elimination for Efficient Point Cloud Registration. [__`reg.`__]
- [[arXiv](https://arxiv.org/pdf/2003.07356.pdf)] Scan2Plan: Efficient Floorplan Generation from 3D Scans of Indoor Scenes. [__`oth.`__]
- [[arXiv](https://arxiv.org/pdf/2003.07717.pdf)] Multimodal Shape Completion via Conditional Generative Adversarial Networks. [__`oth.`__]
- [[arXiv](https://arxiv.org/ftp/arxiv/papers/2002/2002.12573.pdf)] MANet: Multimodal Attention Network based Point-View fusion for 3D Shape Recognition. [__`cls.`__]
- [[arXiv](https://arxiv.org/pdf/2002.08239.pdf)] siaNMS: Non-Maximum Suppression with Siamese Networks for Multi-Camera 3D Object Detection. [__`det.`__]
- [[arXiv](https://arxiv.org/pdf/2003.03653.pdf)] SalsaNext: Fast Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving. [[code](https://github.com/TiagoCortinhal/SalsaNext)] [__`seg.`__]
- [[arXiv](https://arxiv.org/pdf/2003.05982.pdf)] LaserFlow: Efficient and Probabilistic Object Detection and Motion Forecasting. [__`det.`__ __`oth.`__]
- [[arXiv](https://arxiv.org/pdf/2003.06233.pdf)] Feature Fusion Network Based on Attention Mechanism for 3D Semantic Segmentation of Point Clouds. [__`seg.`__]
- [[arXiv](https://arxiv.org/pdf/2003.05505.pdf)] Confidence Guided Stereo 3D Object Detection with Split Depth Estimation. [__`det.`__]
- [[arXiv](https://arxiv.org/pdf/2003.05199.pdf)] Self-supervised Point Set Local Descriptors for Point Cloud Registration. [__`reg.`__]
- [[arXiv](https://arxiv.org/pdf/2003.05410.pdf)] How Powerful Are Randomly Initialized Pointcloud Set Functions?. [__`cls.`__]
- [[arXiv](https://arxiv.org/pdf/2003.05420.pdf)] Bi-Directional Attention for Joint Instance and Semantic Segmentation in Point Clouds. [__`seg.`__]
- [[arXiv](https://arxiv.org/pdf/2003.02392.pdf)] PointLoc: Deep Pose Regressor for LiDAR Point Cloud Localization. [__`oth.`__]
- [[arXiv](https://arxiv.org/pdf/2003.00888.pdf)] 3D Object Detection From LiDAR Data Using Distance Dependent Feature Extraction. [__`det.`__]
- [[arXiv](https://arxiv.org/pdf/2003.00601.pdf)] 3D Point Cloud Processing and Learning for Autonomous Driving. [__`oth.`__]
- [[arXiv](https://arxiv.org/pdf/2002.03281.pdf)] PointHop++: A Lightweight Learning Model on Point Sets for 3D Classification. [[code](https://github.com/minzhang-1/PointHop-PointHop2_Spark)][__`cls.`__]
- [[arXiv](https://arxiv.org/pdf/2003.08624.pdf)] PT2PC: Learning to Generate 3D Point Cloud Shapes from Part Tree Conditions. [[code](https://github.com/daerduoCarey/pt2pc)][__`oth.`__]
- [[arXiv](https://arxiv.org/pdf/2003.07238.pdf)] A Rotation-Invariant Framework for Deep Point Cloud Analysis. [__`oth.`__]
- [[arXiv](https://arxiv.org/pdf/2003.06631.pdf)] Non-Local Part-Aware Point Cloud Denoising. [__`oth.`__]
- [[arXiv](https://arxiv.org/pdf/1912.07009.pdf)] C-Flow: Conditional Generative Flow Models for Images and 3D Point Clouds. [__`oth.`__]
- [[arXiv](https://arxiv.org/pdf/2003.10826.pdf)] DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squares. [__`oth.`__]
- [[arXiv](https://arxiv.org/pdf/2003.10670.pdf)] Real-time 3D object proposal generation and classification under limited processing resources. [__`det.`__]
- [[arXiv](https://www.sciencedirect.com/science/article/abs/pii/S0925231220304070)] Multi-view Semantic Learning Network for Point Cloud Based 3D Object Detection. [__`seg.`__]
- [[arXiv](https://arxiv.org/pdf/2003.08376.pdf)] Sequential Forecasting of 100,000 Points. [__`oth.`__]
- [[arXiv](https://arxiv.org/pdf/2003.08284.pdf)] Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways. [[code](https://github.com/WeikaiTan/Toronto-3D)][__`seg.`__]
- [[arXiv](https://arxiv.org/pdf/2003.12641.pdf)] Self-Supervised Learning for Domain Adaptation on Point-Clouds.[[code](https://github.com/IdanAchituve/DefRec_and_PCM)] [__`oth.`__]
- [[arXiv](https://arxiv.org/pdf/2003.12841.pdf)] A Benchmark for Point Clouds Registration Algorithms. [[code](https://github.com/iralabdisco/point_clouds_registration_benchmark)][__`reg.`__]
- [[arXiv](https://arxiv.org/pdf/2003.12622.pdf)] SceneCAD: Predicting Object Alignments and Layouts in RGB-D Scans.[[code](https://github.com/skanti/SceneCAD)] [__`oth.`__]
- [[arXiv](https://arxiv.org/pdf/2003.12181.pdf)] ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds. [__`oth.`__]
- [[arXiv](https://arxiv.org/pdf/2003.08376.pdf)] Unsupervised Sequence Forecasting of 100,000 Points for Unsupervised Trajectory Forecasting. [[pytorch](https://github.com/xinshuoweng/SPCSF)][__`oth.`__]
- [[arXiv](https://arxiv.org/pdf/2003.14014.pdf)] SK-Net: Deep Learning on Point Cloud via End-to-end Discovery of Spatial Keypoints. [__`cls.`__]
- [[arXiv](https://arxiv.org/pdf/2003.13834.pdf)] Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions. [[pytorch](https://github.com/matheusgadelha/PointCloudLearningACD)][__`oth.`__]
- [[arXiv](https://arxiv.org/pdf/2004.00186.pdf)] Boundary-Aware Dense Feature Indicator for Single-Stage 3D Object Detection from Point Clouds. [__`det.`__]
- [[arXiv](https://arxiv.org/pdf/2003.05420.pdf)] Bi-Directional Attention for Joint Instance and Semantic Segmentation in Point Clouds. [[pytorch](https://github.com/pumpkinnan/BAN)] [__`seg.`__]
- [[arXiv](https://arxiv.org/pdf/2003.13926.pdf)] Scene Context Based Semantic Segmentation for 3D LiDAR Data in Dynamic Scene. [__`seg.`__]
- [[arXiv](https://arxiv.org/abs/2004.01643)] Quantifying Data Augmentation for LiDAR based 3D Object Detection. [[code](https://www.trace.ethz.ch/publications/2020/data_augmentation/)][__`det.`__]
- [[arXiv](https://arxiv.org/abs/2004.01301)] Generative PointNet: Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification. [__`oth.`__]
- [[arXiv](https://arxiv.org/abs/2004.01228)] Deformation-Aware 3D Model Embedding and Retrieval. [__`oth.`__]
- [[arXiv](https://arxiv.org/abs/2004.01661)] Intrinsic Point Cloud Interpolation via Dual Latent Space Navigation. [__`oth.`__]
- [[arXiv](https://arxiv.org/abs/2004.02774)] SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds. [[code](https://github.com/xinge008/SSN)][__`det.`__]
- [[arXiv](https://arxiv.org/abs/2004.02724)] Reconfigurable Voxels: A New Representation for LiDAR-Based Point Clouds. [__`seg.`__]
- [[arXiv](https://arxiv.org/abs/2004.03401)] MNEW: Multi-domain Neighborhood Embedding and Weighting for Sparse Point Clouds Segmentation. [__`seg.`__]
- [[arXiv](https://arxiv.org/abs/2004.04462)] LightConvPoint: convolution for points. [[code](https://github.com/valeoai/LightConvPoint)][__`cls.`__]
- [[arXiv](https://arxiv.org/abs/2004.04962)] 3D IoU-Net: IoU Guided 3D Object Detector for Point Clouds. [__`det.`__]
- [[arXiv](https://arxiv.org/abs/2004.05224)] Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Review. [__`review.`__]
- [[arXiv](https://arxiv.org/abs/2004.05242)] Simulation-based Lidar Super-resolution for Ground Vehicles. [[tensorflow](https://github.com/RobustFieldAutonomyLab/lidar_super_resolution)][__`oth.`__]
- [[arXiv](https://arxiv.org/abs/2004.04242)] Deep Manifold Prior. [__`oth.`__]
- [[arXiv](https://arxiv.org/abs/2004.09057)] Airborne LiDAR Point Cloud Classification with Graph Attention Convolution Neural Network. [__`cls.`__]
- [[arXiv](https://arxiv.org/abs/2004.09061)] Semantic Correspondence via 2D-3D-2D Cycle. [[code](https://github.com/qq456cvb/SemanticTransfer)][__`oth.`__]
- [[arXiv](https://arxiv.org/abs/2004.08596)] DAPnet: A double self-attention convolutional network for segmentation of point clouds. [[code](https://github.com/RayleighChen/point-attention)] [__`seg.`__]
- [[arXiv](https://arxiv.org/abs/2004.11784)] DPDist : Comparing Point Clouds Using Deep Point Cloud Distance. [__`seg.`__]
- [[arXiv](https://arxiv.org/abs/2004.12636)] 3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection. [__`det.`__]
- [[arXiv](https://arxiv.org/abs/2004.12498)] Weakly Supervised Semantic Segmentation in 3D Graph-Structured Point Clouds of Wild Scenes. [__`seg.`__]
- [[arXiv](https://arxiv.org/abs/2004.12989)] CoReNet: Coherent 3D scene reconstruction from a single RGB image. [__`reconstruction.`__]
- [[arXiv](https://arxiv.org/abs/2005.00383)] MOPS-Net: A Matrix Optimization-driven Network forTask-Oriented 3D Point Cloud Downsampling. [__`sampling.`__]
- [[arXiv](https://arxiv.org/abs/2005.02138)] PointTriNet: Learned Triangulation of 3D Point Sets. [__`Triangulation.`__]
- [[arXiv](https://arxiv.org/abs/2005.02696)] Drosophila-Inspired 3D Moving Object Detection Based on Point Clouds. [__`detection.`__]
- [[arXiv](https://arxiv.org/abs/2005.03871)] Point Cloud Completion by Skip-attention Network with Hierarchical Folding. [__`Completion.`__]
- [[arXiv](https://arxiv.org/abs/2005.06734)] Dense-Resolution Network for Point Cloud Classification and Segmentation.[[code](https://github.com/ShiQiu0419/DRNet)] [__`segmentation.`__]
- [[arXiv](https://arxiv.org/abs/2005.06667)] Exploiting Multi-Layer Grid Maps for Surround-View Semantic Segmentation of Sparse LiDAR Data. [__`segmentation.`__]
- [[arXiv](https://arxiv.org/abs/2005.09830)] Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review. [__`Review.`__]
- [[arXiv](https://arxiv.org/abs/2005.11626)] hapeAdv: Generating Shape-Aware Adversarial 3D Point Clouds. [__`Generation.`__]
- [[arXiv](https://arxiv.org/abs/2005.09927)] Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection. [__`Detection.`__]
- [[arXiv](https://arxiv.org/abs/2005.13135)] PAI-Conv: Permutable Anisotropic Convolutional Networks for Learning on Point Clouds. [__`Classification.`__]
- [[arXiv](https://arxiv.org/abs/2005.11626)] ShapeAdv: Generating Shape-Aware Adversarial 3D Point Clouds. [__`Generation.`__]
- [[arXiv](hhttps://arxiv.org/abs/2006.04043)] SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds. [__`Detection.`__]
- [[arXiv](https://arxiv.org/abs/2006.04307)] Are We Hungry for 3D LiDAR Data for Semantic Segmentation? [__`Segmentation.`__]
- [[arXiv](https://arxiv.org/abs/2006.03761)] GRNet: Gridding Residual Network for Dense Point Cloud Completion. [__`Completion.`__]
- [[arXiv](https://arxiv.org/abs/2006.04523)] Learning 3D-3D Correspondences for One-shot Partial-to-partial Registration. [__`Registration.`__]
- [[arXiv](https://arxiv.org/abs/2006.03762)] Deep Octree-based CNNs with Output-Guided Skip Connections for 3D Shape and Scene Completion. [__`Completion.`__]
- [[arXiv](https://arxiv.org/abs/2006.05548)] 3D Point Cloud Feature Explanations Using Gradient-Based Methods. [__`other.`__]
- [[arXiv](https://arxiv.org/abs/2006.05187)] Stereo RGB and Deeper LIDAR Based Network for 3D Object Detection. [__`Detection.`__]
- [[arXiv](https://arxiv.org/pdf/2006.05682.pdf)] H3DNet: 3D Object Detection Using Hybrid Geometric Primitives. [[pytorch](https://github.com/zaiweizhang/H3DNet)][__`Detection.`__]
- [[arXiv](https://arxiv.org/abs/2006.12356)] Generative Sparse Detection Networks for 3D Single-shot Object Detection. [__`Detection.`__]
- [[arXiv](https://arxiv.org/abs/2006.11275)] Center-based 3D Object Detection and Tracking. [[pytorch](https://github.com/tianweiy/CenterPoint)][__`Detection.`__]
- [[arXiv](https://arxiv.org/abs/2006.15505)] 1st Place Solution for Waymo Open Dataset Challenge -- 3D Detection and Domain Adaptation. [__`Detection.`__]
- [[arXiv](https://arxiv.org/abs/2006.15506)] 1st Place Solutions for Waymo Open Dataset Challenges -- 2D and 3D Tracking. [__`Detection.`__]
- [[arXiv](https://arxiv.org/abs/2007.04883)] PIE-NET: Parametric Inference of Point Cloud Edges. [__`Edge Detection.`__]
- [[arXiv](https://arxiv.org/abs/2007.04537)] Point Set Voting for Partial Point Cloud Analysis. [__`Segmentation,Classification,Completion.`__]
- [[arXiv](https://arxiv.org/abs/2007.02571)] Geometric Attention for Prediction of Differential Properties in 3D Point Clouds. [__`Feature Line.`__]
- [[arXiv](https://arxiv.org/abs/2007.02099)] Local Grid Rendering Networks for 3D Object Detection in Point Clouds. [__`Detection.`__]
- [[arXiv](https://arxiv.org/abs/2007.08488)] Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds. [__`Segmentation.`__]
- [[arXiv](https://arxiv.org/abs/2007.08501)] Accelerating 3D Deep Learning with PyTorch3D. [__`PyTorch3D.`__]
- [[arXiv](https://arxiv.org/abs/2007.13373)] Part-Aware Data Augmentation for 3D Object Detection in Point Cloud. [__`Detection.`__]
- [[arXiv](https://arxiv.org/abs/2008.01550)] Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation. [[code](https://github.com/xinge008/Cylinder3D)][__`Segmentation.`__]
- [[arXiv](https://arxiv.org/abs/2008.02792)] CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations. [__`Representation.`__]
- [[arXiv](https://arxiv.org/abs/2008.02986)] Global Context Aware Convolutions for 3D Point Cloud Understanding. [__`Understanding.`__]
- [[arXiv](https://arxiv.org/abs/2008.03560)] LPMNet: Latent Part Modification and Generation for 3D Point Clouds. [__`Generation.`__]
- [[arXiv](https://arxiv.org/abs/2008.03404)] VPC-Net: Completion of 3D Vehicles from MLS Point Clouds. [__`Completion.`__]
- [[arXiv](https://arxiv.org/abs/2008.03928)] Projected-point-based Segmentation: A New Paradigm for LiDAR Point Cloud Segmentation. [__`Segmentation.`__]
- [[arXiv](https://arxiv.org/abs/2008.05242)] PAM:Point-wise Attention Module for 6D Object Pose Estimation. [__`Pose.`__]
- [[arXiv](https://arxiv.org/abs/2008.06471)] Self-Sampling for Neural Point Cloud Consolidation. [__`Consolidation.`__]
- [[arXiv](https://arxiv.org/abs/2008.09527)] Deterministic PointNetLK for Generalized Registration. [__`Registration.`__]
- [[arXiv]( https://arxiv.org/pdf/2009.05307.pdf)] A Density-Aware PointRCNN for 3D Objection Detection in Point Clouds.[__`Detection`__]
- [[arXiv]( https://arxiv.org/pdf/2009.06903.pdf)] A Self Contour-based Rotation and Translation-Invariant Transformation for Point Clouds Recognition.[[code]( https://github.com/shenqildr/ScorNet )] [__`Recognition `__]
- [[arXiv](https://arxiv.org/pdf/2009.08924.pdf)] Multi-Resolution Graph Neural Network for Large-Scale Pointcloud Segmentation. [__`Segmentation`__]
- [[arXiv](https://arxiv.org/pdf/2009.08920.pdf)] Deep Learning for 3D Point Cloud Understanding: A Survey. [[code]( https://github.com/SHI-Labs/3D-Point-Cloud-Learning)] [__`Survey`__]
- [[arXiv](https://arxiv.org/pdf/2009.10569.pdf)] Improving Point Cloud Semantic Segmentation by Learning 3D Object Proposal Generation. [__`Segmentation`__]
- [[arXiv](https://arxiv.org/abs/2009.10945)] MAFF-Net: Filter False Positive for 3D Vehicle Detection with Multi-modal Adaptive Feature Fusion. [__`Detection`__]
- [[arXiv](https://arxiv.org/abs/2010.00321)] Deep-3DAligner: Unsupervised 3D Point Set Registration Network With Optimizable Latent Vector. [__`Registration`__]
- [[arXiv](https://arxiv.org/pdf/2009.13727.pdf)] Graph-based methods for analyzing orchard tree structure using noisy point cloud data. [__` `__]
- [[arXiv](https://arxiv.org/pdf/2010.01089.pdf)] Pre-Training by Completing Point Clouds[[torch]( https://github.com/hansen7/OcCo)]. [__`Completion`__]
- [[arXiv](https://arxiv.org/pdf/2010.00820.pdf)] Discriminative and Generative Models for Anatomical Shape Analysis on Point Clouds with Deep Neural Networks . [__`Analysis `__]
- [[arXiv](https://arxiv.org/pdf/2010.00824.pdf)] Goal-Auxiliary Actor-Critic for 6D Robotic Grasping with Point Clouds. [__`Grasping`__]
- [[arXiv](https://arxiv.org/pdf/2010.02449.pdf)] On the Universality of Rotation Equivariant Point Cloud Networks.[__` Analysis `__]
- [[arXiv](https://arxiv.org/pdf/2010.03506.pdf)] Learning Monocular 3D Vehicle Detection without 3D Bounding Box Labels. [__`Detection `__]
- [[arXiv](https://arxiv.org/pdf/2010.04642.pdf)] Torch-Points3D: A Modular Multi-Task Framework for Reproducible Deep Learning on 3D Point Clouds.[[torch]( https://github.com/nicolas-chaulet/torch-points3d)][__`Framework`__]
- [[arXiv](https://arxiv.org/pdf/2010.04278.pdf)] Refinement of Predicted Missing Parts Enhance Point Cloud Completion.[[torch]( https://github.com/ivansipiran/Refinement-Point-Cloud-Completion)][__` Completion `__]
- [[arXiv](https://arxiv.org/pdf/2010.08719.pdf)] A Self-supervised Cascaded Refinement Network for Point Cloud Completion. [__` Completion`__]
- [[arXiv](https://arxiv.org/pdf/2010.09079.pdf)] Graphite: GRAPH-Induced feaTure Extraction for Point Cloud Registration. [__` Registration`__]
- [[arXiv](https://arxiv.org/pdf/2010.09582.pdf)] Learning to Reconstruct and Segment 3D Objects. [__` Segmentation；Reconstruction`__]
- [[arXiv](https://arxiv.org/pdf/2010.08744.pdf)] Generating Large Convex Polytopes Directly on Point Clouds. [__` Segmentation `__]
- [[arxiv]( https://arxiv.org/pdf/2010.08092.pdf)] Human Segmentation with Dynamic LiDAR Data. [__` Segmentation`__]
- [[arXiv](https://arxiv.org/pdf/2010.11087.pdf)] Representing Point Clouds with Generative Conditional Invertible Flow Networks. [__`Representation`__]
- [[arXiv](https://arxiv.org/pdf/2010.11159.pdf)] 3D Meta Point Signature: Learning to Learn 3D Point Signature for 3D Dense Shape Correspondence. [__`Correspondence`__]
- [[arXiv](https://arxiv.org/pdf/2010.11702.pdf)] MLOD: Awareness of Extrinsic Perturbation in Multi-LiDAR 3D Object Detection for Autonomous Driving.[[code](http://143.89.78.112:5000/sharing/90BpyDIuq)][__`Detection `__]
- [[arXiv](https://arxiv.org/pdf/2010.11504.pdf)] 3D Meta-Registration: Learning to Learn Registration of 3D Point Clouds. [__`Registration `__]
- [[arXiv](https://arxiv.org/abs/2011.00652)] Multi-View Adaptive Fusion Network for 3D Object Detection. [__`Detection`__]
- [[arXiv](https://arxiv.org/abs/2011.00923)] MARNet: Multi-Abstraction Refinement Network for 3D Point Cloud Analysis. [[code](https://github.com/ruc98/MARNet)][__`Analysis`__]
- [[arXiv](https://arxiv.org/abs/2011.00931)] Point Transformer. [__`Analysis`__]
- [[arXiv](https://arxiv.org/abs/2011.01404)] Faraway-Frustum: Dealing with Lidar Sparsity for 3D Object Detection using Fusion. [__`Detection`__]
- [[arXiv](https://arxiv.org/abs/2010.05501)] BiPointNet: Binary Neural Network for Point Clouds. [__`Analysis`__]
- [[arXiv](https://arxiv.org/abs/2011.09080)] Deep Positional and Relational Feature Learning for Rotation-Invariant Point Cloud Analysis. [__`Rotation`__]
- [[arXiv](https://arxiv.org/abs/2011.12001)] Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes. [[code](https://github.com/qq456cvb/CanonicalVoting)][__`Detection`__]
- [[arXiv](https://arxiv.org/abs/2011.12149)] SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration. [[code](https://github.com/QingyongHu/SpinNet)][__`Registration`__]
- [[arXiv](https://arxiv.org/abs/2011.12079)] Multi-Features Guidance Network for partial-to-partial point cloud registration. [__`registration`__]
- [[arXiv](https://arxiv.org/abs/2011.10812)] MoNet: Motion-based Point Cloud Prediction Network. [__`Motion`__]
- [[arXiv](https://arxiv.org/abs/2011.12888)] Recalibration of Neural Networks for Point Cloud Analysis. [__`Recalibration`__]
- [[arXiv](https://arxiv.org/abs/2011.12745)] Deep Magnification-Arbitrary Upsampling over 3D Point Clouds. [__`Upsampling`__]
- [[arXiv](https://arxiv.org/abs/2011.13849)] Robust Detection of Non-overlapping Ellipses from Points with Applications to Circular Target Extraction in Images and Cylinder Detection in Point Clouds.[__`Detection`__]
- [[arXiv](https://arxiv.org/abs/2011.13784)] Spherical Interpolated Convolutional Network with Distance-Feature Density for 3D Semantic Segmentation of Point Clouds.[__` Segmentation`__]
- [[arXiv](https://arxiv.org/abs/2011.13328)] DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution.[[code](https://github.com/aim-uofa/DyCo3D)][__`Segmentation `__]
- [[arXiv](https://arxiv.org/abs/2011.13005)] PREDATOR: Registration of 3D Point Clouds with Low Overlap.[__`Registration `__]
- [[arXiv](https://arxiv.org/pdf/2011.14700.pdf)] Learning-based lossless compression of 3D point cloud geometry.[__`Compression`__]
- [[arXiv](https://arxiv.org/pdf/2011.14880.pdf)] Occlusion Guided Scene Flow Estimation on 3D Point Clouds.[__`Flow`__]
- [[arXiv](https://arxiv.org/pdf/2011.14289.pdf)] Learning geometry-image representation for 3D point cloud generation.[__`Generation`__]
- [[arXiv](https://arxiv.org/pdf/2011.14285.pdf)] Deeper or Wider Networks of Point Clouds with Self-attention?[__`Networks`__]
- [[arXiv](https://arxiv.org/pdf/2011.15081.pdf)] DEF: Deep Estimation of Sharp Geometric Features in 3D Shapes[__`Features`__]
- [[arXiv](https://arxiv.org/abs/2012.04934)] AMVNet: Assertion-based Multi-View Fusion Network for LiDAR Semantic Segmentation.[__`Segmentation`__]
- [[arXiv](https://arxiv.org/abs/2012.05018)] vLPD-Net: A Registration-aided Domain Adaptation Network for 3D Point Cloud Based Place Recognition.[__`Registration`__]
- [[arXiv](https://arxiv.org/abs/2012.04355)] 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection.[[code](https://github.com/THU17cyz/3DIoUMatch)][__`Detection `__]
- [[arXiv](https://arxiv.org/abs/2012.04439)] SPU-Net: Self-Supervised Point Cloud Upsampling by Coarse-to-Fine Reconstruction with Self-Projection Optimization.[__`Upsampling`__]
- [[arXiv](https://arxiv.org/abs/2012.03028)] ParaNet: Deep Regular Representation for 3D Point Clouds.[__`Representation`__]
-
- [[IROS](https://arxiv.org/abs/2011.00988)] PBP-Net: Point Projection and Back-Projection Network for 3D Point Cloud Segmentation. [__`Segmentation `__]
- [[IROS](http://ras.papercept.net/images/temp/IROS/files/0144.pdf)] RegionNet: Region-feature-enhanced 3D Scene Understanding Network with Dual Spatial-aware Discriminative Loss. [__`Segmentation `__]
- [[IROS](https://arxiv.org/pdf/2007.15488.pdf)] Cascaded Non-local Neural Network for Point Cloud Semantic Segmentation. [__`Segmentation`__]
- [[IROS](https://arxiv.org/pdf/2007.13715.pdf)] Point Cloud Based Reinforcement Learning for Sim-to-Real and Partial Observability in Visual Navigation. [__`Navigation`__]
- [[IROS](https://arxiv.org/pdf/2008.05309.pdf)] Factor Graph based 3D Multi-Object Tracking in Point Clouds. [__`Tracking`__]
- [[IROS](https://arxiv.org/pdf/2008.11459.pdf)] Semantic Graph Based Place Recognition for 3D Point Clouds. [__`Place Recognition`__]
- [[IROS](http://ras.papercept.net/images/temp/IROS/files/1208.pdf)] PillarFlowNet: A Real-time Deep Multitask Network for LiDAR-based 3D Object Detection and Scene Flow Estimation. [__`Detection, Flow`__]
- [[IROS](https://arxiv.org/pdf/2011.14579.pdf)] End-to-End 3D Point Cloud Learning for Registration Task Using Virtual Correspondences.[__` Registration `__]
-
- [[3DV](https://arxiv.org/pdf/2010.08243.pdf)] SF-UDA3D: Source-Free Unsupervised Domain Adaptation for LiDAR-Based 3D Object Detection. [__`Detection`__]
- [[3DV](https://arxiv.org/abs/2011.00320)] Scene Flow from Point Clouds with or without Learning. [__`Flow `__]
- [[3DV](https://arxiv.org/abs/2011.02229)] Registration Loss Learning for Deep Probabilistic Point Set Registration. [[pytorch](https://github.com/felja633/RLLReg)][__` Registration`__]
- [[3DV](https://arxiv.org/abs/2010.09185)] MaskNet: A Fully-Convolutional Network to Estimate Inlier Points. [[pytorch](https://github.com/vinits5/masknet)][__` Registration`__]
-
- [[ACM MM](https://arxiv.org/pdf/2007.13970.pdf)] Weakly Supervised 3D Object Detection from Point Clouds. [[code](https://github.com/Zengyi-Qin/Weakly-Supervised-3D-Object-Detection)][__`Detection`__]
- [[ACM MM](https://arxiv.org/pdf/2007.13551.pdf)] Differentiable Manifold Reconstruction for Point Cloud Denoising. [[pytorch](https://github.com/luost26/DMRDenoise)][__`Denoising`__]
- [[ACM MM](https://arxiv.org/pdf/2008.04968.pdf)] Campus3D: A Photogrammetry Point Cloud Benchmark for Hierarchical Understanding of Outdoor Scene. [__`Understanding`__]
-
- [[WACV](https://arxiv.org/pdf/1912.08487.pdf)] FuseSeg: LiDAR Point Cloud Segmentation Fusing Multi-Modal Data. [__`seg.`__ __`aut.`__]
- [[WACV](http://openaccess.thecvf.com/content_WACV_2020/papers/Ma_Global_Context_Reasoning_for_Semantic_Segmentation_of_3D_Point_Clouds_WACV_2020_paper.pdf)] Global Context Reasoning for Semantic Segmentation of 3D Point Clouds. [__`seg.`__]
- [[WACV](http://openaccess.thecvf.com/content_WACV_2020/papers/Chen_PonitPoseNet_Point_Pose_Network_for_Robust_6D_Object_Pose_Estimation_WACV_2020_paper.pdf)] PointPoseNet: Point Pose Network for Robust 6D Object Pose Estimation. [__`oth.`__]
-
- [[BMVC](https://arxiv.org/pdf/2008.05149.pdf)] ASAP-Net: Attention and Structure Aware Point Cloud Sequence Segmentation. [__`Segmentation`__]
-
- [[NIPS](https://arxiv.org/pdf/2010.03318.pdf)] Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloud. [__`Representation`__]
- [[NIPS](https://papers.nips.cc/paper/2020/file/fc152e73692bc3c934d248f639d9e963-Paper.pdf)] MuSCLE: Multi Sweep Compression of LiDAR using Deep Entropy Models. [__`Compression`__]
- [[NIPS](https://papers.nips.cc/paper/2020/file/9b72e31dac81715466cd580a448cf823-Paper.pdf)] Group Contextual Encoding for 3D Point Clouds. [__`Detection`__]
-
- [[ICML](https://arxiv.org/pdf/2007.04525.pdf)] PointMask: Towards Interpretable and Bias-Resilient Point Cloud Processing. [__`Classification.`__]
-
- [[ICRA](https://arxiv.org/pdf/2003.08624.pdf)] DeepTemporalSeg: Temporally Consistent Semantic Segmentation of 3D LiDAR Scans. [__`seg.`__]
- [[ICRA](https://arxiv.org/abs/1909.07137v1)] PLIN: A Network for Pseudo-LiDAR Point Cloud Interpolation. [__`completion.`__]
- [[ICRA](https://francisengelmann.github.io/DPC/engelmann_icra2020_dpc.pdf)] Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds. [__`cls.`__]
- [[ICRA](https://arxiv.org/abs/2004.11647)] Any Motion Detector: Learning Class-agnostic Scene Dynamics from a Sequence of LiDAR Point Clouds. [__`det.`__]
-
- [[TPAMI](https://arxiv.org/pdf/1909.09287.pdf)] Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds. [__`cls.`__]
-
- [[ICLR](https://arxiv.org/pdf/1904.00069.pdf)] Unpaired Point Cloud Completion on Real Scans using Adversarial Training.[[tensorflow](https://github.com/ChenXuelinCXL/pcl2pcl-gan-pub )] [__`com.`__]
-
- [[ACIIDS](https://link.springer.com/chapter/10.1007/978-3-030-41964-6_41)] Semi-supervised Representation Learning for 3D Point Clouds. [__`oth.`__]
-
- [[CG](https://www.sciencedirect.com/science/article/abs/pii/S0097849320300224)] ConvPoint: Continuous convolutions for point cloud processing. [__`oth.`__]
-
- [[ISPRS](https://www.sciencedirect.com/science/article/abs/pii/S0924271620300605)] Deep point embedding for urban classification using ALS point clouds: A new perspective from local to global. [__`oth.`__]
-
- [[GMP](https://arxiv.org/pdf/2003.08240.pdf)] LRC-Net: Learning Discriminative Features on Point Clouds by EncodingLocal Region Contexts. [__`cls.`__]
-
- [[SPM](https://arxiv.org/abs/2004.11563)] Deep Feature-preserving Normal Estimation for Point Cloud Filtering. [__`normal.`__]
-
- [[Master Thesis](https://pdfs.semanticscholar.org/4303/8a62b3e3b2f44d7a9cc50ff69e7586a758cc.pdf)] Neighborhood Pooling in Graph Neural Networks for 3D and 4D Semantic Segmentation. [__'seg.'__]
---
## 2021
- [[arXiv](https://arxiv.org/abs/2012.11409)] 3D Object Detection with Pointformer. [__`Detection.`__]
- [[arXiv](https://arxiv.org/abs/2011.13328)] DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution. [__`Segmentation.`__]
- [[arXiv](https://arxiv.org/abs/2012.10217)] SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation. [__`Segmentation.`__]
- [[arXiv](https://arxiv.org/abs/2012.10412)] PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection. [__`Detection.`__]
- [[arXiv](https://arxiv.org/ftp/arxiv/papers/2012/2012.10192.pdf)] LGENet: Local and Global Encoder Network for Semantic Segmentation of Airborne Laser Scanning Point Clouds. [__`Segmentation.`__]
- [[arXiv](https://arxiv.org/abs/2012.10042)] 3D Object Classification on Partial Point Clouds: A Practical Perspective. [__`Classification.`__]
- [[arXiv](https://arxiv.org/abs/2012.10066)] PointINet: Point Cloud Frame Interpolation Network. [__`Detection.`__]
- [[arXiv](https://arxiv.org/abs/2012.09418)] PanoNet3D: Combining Semantic and Geometric Understanding for LiDARPoint Cloud Detection. [__`Detection.`__]
- [[arXiv](https://arxiv.org/abs/2012.09688)] PCT: Point Cloud Transformer. [__`Transformer.`__]
- [[arXiv](https://arxiv.org/abs/2012.09793)] SceneFormer: Indoor Scene Generation with Transformers. [__`Transformer.`__]
- [[arXiv](https://arxiv.org/abs/2012.09165)] Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. [__`Understanding.`__]
- [[arXiv](https://arxiv.org/abs/2101.02374)] Efficient 3D Point Cloud Feature Learning for Large-Scale Place Recognition. [[tensorflow](https://github.com/fpthink/EPC-Net)] [__`Place Recognition.`__]
- [[arXiv](https://arxiv.org/abs/2101.02691)] Self-Supervised Pretraining of 3D Features on any Point-Cloud.[[pytorch](https://github.com/facebookresearch/DepthContrast)] [__`Self-Supervised.`__]
- [[arXiv](https://arxiv.org/abs/2101.02672)] Self-Attention Based Context-Aware 3D Object Detection. [[pytorch](https://github.com/AutoVision-cloud/SA-Det3D)] [__`Detection.`__]
- [[arXiv](https://arxiv.org/abs/2102.00463)] PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection [[pytorch](https://github.com/open-mmlab/OpenPCDet)] [__`Detection.`__]
- [[arXiv](https://arxiv.org/abs/2102.03747)] DPointNet: A Density-Oriented PointNet for 3D Object Detection in Point Clouds. [__`Detection.`__]
- [[arXiv](https://arxiv.org/abs/2102.04136)] Points2Vec: Unsupervised Object-level Feature Learning from Point Clouds. [__`Learning.`__]
- [[arXiv](https://arxiv.org/abs/2102.04014)] Point-set Distances for Learning Representations of 3D Point Clouds. [__`Distances.`__]
- [[arXiv](https://arxiv.org/abs/2102.08945)] Weakly Supervised Learning of Rigid 3D Scene Flow. [[pytorch](https://github.com/zgojcic/Rigid3DSceneFlow)] [__`Scene Flow.`__]
- [[arXiv](https://arxiv.org/abs/2102.10788)] Attention Models for Point Clouds in Deep Learning: A Survey. [__`Survey.`__]
- [[arXiv](https://arxiv.org/abs/2102.13391)] Point Cloud Upsampling and Normal Estimation using Deep Learning for Robust Surface Reconstruction. [__`Upsampling.`____`Reconstruction.`__]
-
- [[ICLR](https://openreview.net/pdf?id=O3bqkf_Puys)] PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences. [__`Sequences`__]
- [[ICLR](https://openreview.net/pdf?id=rABUmU3ulQh)] Learning to Generate 3D Shapes with Generative Cellular Automata. [__`Generation`__]
-
- [[TOG](https://arxiv.org/abs/2011.01630)] PCEDNet : A Lightweight Neural Network for Fast and Interactive Edge Detection in 3D Point Clouds [__`Edge Detection.`__]
-
- [[CoRL](https://arxiv.org/abs/2110.04076)] Self-supervised Point Cloud Prediction Using 3D Spatio-temporal Convolutional Networks. [[code](github.com/PRBonn/point-cloud-prediction)] [__`Prediction.`__]
-
- [[CVPR](https://arxiv.org/pdf/2103.01458v1.pdf)] Diffusion Probabilistic Models for 3D Point Cloud Generation. [[code](https://github.com/luost26/diffusion-point-cloud)][__`Generation`__]
- [[CVPR](https://arxiv.org/pdf/2011.13005.pdf)] PREDATOR: Registration of 3D Point Clouds with Low Overlap. [[pytorch](https://github.com/ShengyuH/OverlapPredator)][__`Registration`__]
- [[CVPR](https://arxiv.org/abs/2103.02535)] Style-based Point Generator with Adversarial Rendering for Point Cloud Completion. [__`Completion`__]
- [[CVPR](https://github.com/QingyongHu/SpinNet)] SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration. [[pytorch](https://github.com/QingyongHu/SpinNet)][__`Registration`__]
- [[CVPR oral](https://arxiv.org/abs/2101.06605)] MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization. [[code](https://github.com/huangjh-pub/multibody-sync)][__`Synchronization`__]
- [[CVPR](https://arxiv.org/abs/2006.11275)] Center-based 3D Object Detection and Tracking. [[pytorch](https://github.com/tianweiy/CenterPoint)][__`Detection`__]
- [[CVPR](https://arxiv.org/abs/2012.04355)] 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection. [[pytorch](https://github.com/thu17cyz/3DIoUMatch)][__`Detection`__]
- [[CVPR](https://arxiv.org/abs/2103.03046)] PointGuard: Provably Robust 3D Point Cloud Classification. [__`Classification`__]
- [[CVPR](https://arxiv.org/abs/2103.03067)] TPCN: Temporal Point Cloud Networks for Motion Forecasting. [__`Motion`__]
- [[CVPR](https://arxiv.org/abs/2009.03137)] Towards Semantic Segmentation of Urban-Scale 3D Point Clouds: A Dataset, Benchmarks and Challenges. [[code](https://github.com/QingyongHu/SensatUrban)][__`Segmentation`__]
- [[CVPR](https://arxiv.org/abs/2103.04256)] Robust Point Cloud Registration Framework Based on Deep Graph Matching. [[code](https://github.com/fukexue/RGM)][__`Registration`__]
- [[CVPR](https://arxiv.org/abs/2103.05346)] ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection. [[code](https://github.com/CVMI-Lab/ST3D)][__`Detection`__]
- [[CVPR](https://arxiv.org/abs/2103.05465)] PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency. [__`Registration`__]
- [[CVPR](https://arxiv.org/abs/2103.05558)] Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis. [__`Scene analysis`__]
- [[CVPR](https://arxiv.org/abs/2103.05086)] How Privacy-Preserving are Line Clouds? Recovering Scene Details from 3D Lines. [[code](https://github.com/kunalchelani/Line2Point)][__`Scene recover`__]
- [[CVPR](https://enigma-li.github.io/projects/point2skeleton/point2skeleton.html)] Point2Skeleton: Learning Skeletal Representations from Point Clouds. [[code](https://github.com/clinplayer/Point2Skeleton)][__`Skeleton`__]
- [[CVPR](https://arxiv.org/abs/2103.07838)] Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding. [__`Completion`__]
- [[CVPR](https://arxiv.org/abs/2103.07969)] Monte Carlo Scene Search for 3D Scene Understanding. [__`Understanding`__]
- [[CVPR](https://arxiv.org/abs/2102.04530)] AF2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network. [__`Segmentation`__]
- [[CVPR](https://arxiv.org/abs/2103.14147)] Equivariant Point Network for 3D Point Cloud Analysis. [__`Analysis`__]
- [[CVPR](https://arxiv.org/abs/2103.14635)] PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds. [[code](https://github.com/CVMI)][__`Convolution`__]
- [[CVPR](http://arxiv.org/abs/1912.00145)] Point Cloud Instance Segmentation using Probabilistic Embeddings. [__`Segmentation`__]
- [[CVPR](https://arxiv.org/abs/2103.14962)] Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation. [__`Segmentation`__]
- [[CVPR](https://arxiv.org/abs/2103.15231)] ReAgent: Point Cloud Registration using Imitation and Reinforcement Learning. [__`Registration`__]
- [[CVPR](https://arxiv.org/abs/2103.15297)] LiDAR R-CNN: An Efficient and Universal 3D Object Detector. [[code](https://github.com/tusimple/LiDAR_RCNN)][__`Detection`__]
- [[CVPR](https://arxiv.org/abs/2104.00902)] HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detection. [__`Detection`__]
- [[CVPR](https://arxiv.org/abs/2104.00798)] FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point Clouds. [__`Flow`__]
- [[CVPR](https://arxiv.org/abs/2104.03501)] DeepI2P: Image-to-Point Cloud Registration via Deep Classification. [[code](https://github.com/lijx10/DeepI2P)][__`Registration`__]
- [[CVPR](https://arxiv.org/abs/2104.06114)] Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds. [[pytorch](https://github.com/cheng052/BRNet)][__`Detection`__]
- [[CVPR](https://arxiv.org/abs/2104.13366)] Unsupervised 3D Shape Completion through GAN Inversion. [[pytorch](https://github.com/junzhezhang/shape-inversion)][__`Completion`__]
- [[CVPR](https://arxiv.org/abs/2104.09804)] SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud. [[code](https://github.com/Vegeta2020/SE-SSD)][__`Detection`__]
- [[CVPR oral](https://hehefan.github.io/pdfs/p4transformer.pdf)] Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos. [[pytorch](https://github.com/hehefan/P4Transformer)][__`Transformer`__]
- [[CVPR](https://arxiv.org/abs/2105.02158)] VoxelContext-Net: An Octree based Framework for Point Cloud Compression. [__`Compression`__]
- [[CVPR](https://arxiv.org/abs/2105.07751)] HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embedding. [__`Flow`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Qi_Offboard_3D_Object_Detection_From_Point_Cloud_Sequences_CVPR_2021_paper.pdf)] Offboard 3D Object Detection from Point Cloud Sequences. [__`Detection`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Zeng_CorrNet3D_Unsupervised_End-to-End_Learning_of_Dense_Correspondence_for_3D_Point_CVPR_2021_paper.pdf)] CorrNet3D: Unsupervised End-to-End Learning of Dense Correspondence for 3D Point Clouds. [[code](https://github.com/ZENGYIMING-EAMON/CorrNet3D)][__`Correspondence`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Li_Self-Point-Flow_Self-Supervised_Scene_Flow_Estimation_From_Point_Clouds_With_Optimal_CVPR_2021_paper.pdf)] Self-Point-Flow: Self-Supervised Scene Flow Estimation From Point Clouds With Optimal Transport and Random Walk. [__`Flow`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Xia_SOE-Net_A_Self-Attention_and_Orientation_Encoding_Network_for_Point_Cloud_CVPR_2021_paper.pdf)] SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud Based Place Recognition. [[code](https://github.com/Yan-Xia/SOE-Net)][__`Recognition`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Qiu_Semantic_Segmentation_for_Real_Point_Cloud_Scenes_via_Bilateral_Augmentation_CVPR_2021_paper.pdf)] Semantic Segmentation for Real Point Cloud Scenes via Bilateral Augmentation and Adaptive Fusion. [__`Segmentation`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Chen_Equivariant_Point_Network_for_3D_Point_Cloud_Analysis_CVPR_2021_paper.pdf)] Equivariant Point Network for 3D Point Cloud Analysis. [[code](https://github.com/nintendops/EPN_PointCloud)][__`Analysis`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Yi_Complete__Label_A_Domain_Adaptation_Approach_to_Semantic_Segmentation_CVPR_2021_paper.pdf)] Complete & Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds. [__`Segmentation`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Lee_Regularization_Strategy_for_Point_Cloud_via_Rigidly_Mixed_Sample_CVPR_2021_paper.pdf)] Regularization Strategy for Point Cloud via Rigidly Mixed Sample. [__`Regularization`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Fischer_StickyPillars_Robust_and_Efficient_Feature_Matching_on_Point_Clouds_Using_CVPR_2021_paper.pdf)] StickyPillars: Robust and Efficient Feature Matching on Point Clouds Using Graph Neural Networks. [__`Matching`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Shen_Verifiability_and_Predictability_Interpreting_Utilities_of_Network_Architectures_for_Point_CVPR_2021_paper.pdf)] Verifiability and Predictability: Interpreting Utilities of Network Architectures for Point Cloud Processing. [__`Processing`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Qian_PU-GCN_Point_Cloud_Upsampling_Using_Graph_Convolutional_Networks_CVPR_2021_paper.pdf)] PU-GCN: Point Cloud Upsampling using Graph Convolutional Networks. [[code](https://github.com/guochengqian/PU-GCN)][__`Upsampling`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Fan_SCF-Net_Learning_Spatial_Contextual_Features_for_Large-Scale_Point_Cloud_Segmentation_CVPR_2021_paper.pdf)] SCF-Net: Learning Spatial Contextual Features for Large-Scale Point Cloud Segmentation.[[code](https://github.com/leofansq/SCF-Net)] [__`Segmentation`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Banani_UnsupervisedRR_Unsupervised_Point_Cloud_Registration_via_Differentiable_Rendering_CVPR_2021_paper.pdf)] UnsupervisedR&R: Unsupervised Point Cloud Registration via Differentiable Rendering. [__`Registration`__]
- [[CVPR](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 Learning on 3D Point Clouds by Learning Discrete Generative Models. [__`Self-Supervised`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Zhao_Sign-Agnostic_Implicit_Learning_of_Surface_Self-Similarities_for_Shape_Modeling_and_CVPR_2021_paper.pdf)] Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction From Raw Point Clouds. [__`Self-Similarities`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Wen_Learning_Progressive_Point_Embeddings_for_3D_Point_Cloud_Generation_CVPR_2021_paper.pdf)] Learning Progressive Point Embeddings for 3D Point Cloud Generation. [__`Generation`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/He_DyCo3D_Robust_Instance_Segmentation_of_3D_Point_Clouds_Through_Dynamic_CVPR_2021_paper.pdf)] DyCo3D: Robust Instance Segmentation of 3D Point Clouds Through Dynamic Convolution. [[code](https://git.io/DyCo3D)][__`Segmentation`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Pang_TearingNet_Point_Cloud_Autoencoder_To_Learn_Topology-Friendly_Representations_CVPR_2021_paper.pdf)] TearingNet: Point Cloud Autoencoder To Learn Topology-Friendly Representations. [__`Autoencoder`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Wang_PWCLO-Net_Deep_LiDAR_Odometry_in_3D_Point_Clouds_Using_Hierarchical_CVPR_2021_paper.pdf)] PWCLO-Net: Deep LiDAR Odometry in 3D Point Clouds Using Hierarchical Embedding Mask Optimization. [[code](https://github.com/IRMVLab/PWCLONet)][__`Odometry`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Wei_PV-RAFT_Point-Voxel_Correlation_Fields_for_Scene_Flow_Estimation_of_Point_CVPR_2021_paper.pdf)] PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds. [__`Flow`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Lu_CGA-Net_Category_Guided_Aggregation_for_Point_Cloud_Semantic_Segmentation_CVPR_2021_paper.pdf)] CGA-Net: Category Guided Aggregation for Point Cloud Semantic Segmentation. [__`Segmentation`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Li_Point_Cloud_Upsampling_via_Disentangled_Refinement_CVPR_2021_paper.pdf)] Point Cloud Upsampling via Disentangled Refinement. [[code](https://github.com/liruihui/Dis-PU)][__`Upsampling`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Wen_PMP-Net_Point_Cloud_Completion_by_Learning_Multi-Step_Point_Moving_Paths_CVPR_2021_paper.pdf)] PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Paths. [[code](https://github.com/diviswen/PMP-Net)][__`Completion`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Zhang_View-Guided_Point_Cloud_Completion_CVPR_2021_paper.pdf)] View-Guided Point Cloud Completion. [__`Completion`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/papers/Zhao_Few-Shot_3D_Point_Cloud_Semantic_Segmentation_CVPR_2021_paper.pdf)] Few-shot 3D Point Cloud Semantic Segmentation. [[code](https://github.com/Na-Z/attMPTI)][__`Segmentation`__]
- [[CVPR](https://facebookresearch.github.io/WyPR/)] 3D Spatial Recognition without Spatially Labeled 3D. [[code](https://facebookresearch.github.io/WyPR/)][__`Detection`__]
- [[CVPR](https://arxiv.org/abs/2103.10814)] Skeleton Merger: an Unsupervised Aligned Keypoint Detector. [[code](https://github.com/eliphatfs/SkeletonMerger)][__`Skeleton`__]
- [[CVPR](https://paul007pl.github.io/projects/VRCNet.html)] Variational Relational Point Completion Network. [[code](https://paul007pl.github.io/projects/VRCNet.html)][__`Completion`__]
- [[CVPR](https://arxiv.org/abs/2103.16671)] DeCo: Denoise and Contrast for Category Agnostic Shape Completion. [[code](https://github.com/antoalli/Deco)][__`Completion`__]
- [[CVPR](https://arxiv.org/pdf/2008.09527.pdf)] PointNetLK Revisited. [[code](https://github.com/Lilac-Lee/PointNetLK_Revisited)][__`Registration`__]
- [[CVPR](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)] PVGNet: A Bottom-Up One-Stage 3D Object Detector With Integrated Multi-Level Features. [__`Detection`__]
-
- [[ICCV](https://arxiv.org/abs/2108.04023)] DRINet: A Dual-Representation Iterative Learning Network for Point Cloud Segmentation. [__`Segmentation`__]
- [[ICCV](https://arxiv.org/abs/2108.03746)] Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projection Matching. [[code](https://github.com/chenchao15/2D_projection_matching?utm_source=catalyzex.com)][__`Generation`__]
- [[ICCV](https://arxiv.org/abs/2107.10981)] Score-Based Point Cloud Denoising. [__`Denoising`__]
- [[ICCV](https://arxiv.org/abs/2107.11992)] HRegNet: A Hierarchical Network for Large-scale Outdoor LiDAR Point Cloud Registration. [[code](https://ispc-group.github.io/hregnet?utm_source=catalyzex.com)][__`Registration`__]
- [[ICCV oral](https://arxiv.org/abs/2108.03257)] (Just) A Spoonful of Refinements Helps the Registration Error Go Down. [__`Registration`__]
- [[ICCV](https://arxiv.org/abs/2107.11769)] ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation. [__`Segmentation`__]
- [[ICCV](https://arxiv.org/abs/2107.14230)] Learning with Noisy Labels for Robust Point Cloud Segmentation. [[code](https://shuquanye.com/PNAL_website/)][__`Segmentation`__]
- [[ICCV](https://arxiv.org/abs/2108.08035)] Adaptive Graph Convolution for Point Cloud Analysis. [[pytorch](https://github.com/hrzhou2/AdaptConv-master)][__`Analysis`__]
- [[ICCV](https://arxiv.org/abs/2108.08187)] ME-PCN: Point Completion Conditioned on Mask Emptiness. [__`Completion`__]
- [[ICCV](https://arxiv.org/abs/2108.07794)] RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detection. [__`Detection`__]
- [[ICCV](https://arxiv.org/abs/2108.07478)] Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks. [[code](https://github.com/Gorilla-Lab-SCUT/SSTNet)][__`Segmentation`__]
- [[ICCV](https://arxiv.org/abs/2108.02350)] Hierarchical Aggregation for 3D Instance Segmentation. [[code](https://github.com/hustvl/HAIS)][__`Segmentation`__]
- [[ICCV](https://arxiv.org/abs/2108.12468)] Learning Inner-Group Relations on Point Clouds. [__`Learning`__]
- [[ICCV](https://arxiv.org/abs/2108.11682)] A Robust Loss for Point Cloud Registration. [__`Registration`__]
- [[ICCV](https://arxiv.org/abs/2108.10723)] Improving 3D Object Detection with Channel-wise Transformer. [__`Detection`__]
- [[ICCV](https://arxiv.org/abs/2109.00179)] patio-temporal Self-Supervised Representation Learning for 3D Point Clouds. [__`Learning`__]
- [[ICCV](https://arxiv.org/abs/2109.02499)] Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection. [__`Detection`__]
- [[ICCV](https://arxiv.org/abs/2109.02497)] Voxel Transformer for 3D Object Detection. [__`Detection`__]
- [[ICCV](https://arxiv.org/abs/2109.04310)] Deep Hough Voting for Robust Global Registration. [__`Registration`__]
- [[ICCV](https://arxiv.org/abs/2108.04444)] SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer. [[code](https://github.com/AllenXiangX/SnowflakeNet)][__`Completion`__]
- [[ICCV](https://arxiv.org/abs/2012.09164)] Point Transformer. [__`Transformer`__]
- [[ICCV](https://arxiv.org/abs/2104.00678)] Group-Free 3D Object Detection via Transformers. [[code](https://github.com/zeliu98/Group-Free-3D)][__`Detection`__]
- [[ICCV](https://arxiv.org/abs/2109.06619)] Sampling Network Guided Cross-Entropy Method for Unsupervised Point Cloud Registration. [__`Registration`__]
- [[ICCV oral](https://arxiv.org/abs/2109.08141)] An End-to-End Transformer Model for 3D Object Detection. [[code](https://github.com/facebookresearch/3detr)][__`Detection`__]
- [[ICCV](https://arxiv.org/abs/2101.02691)] Self-Supervised Pretraining of 3D Features on any Point-Cloud. [[code](https://github.com/facebookresearch/DepthContrast)][__`Detection`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Xu_SPG_Unsupervised_Domain_Adaptation_for_3D_Object_Detection_via_Semantic_ICCV_2021_paper.pdf)] SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation. [__`Detection`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Xie_VENet_Voting_Enhancement_Network_for_3D_Object_Detection_ICCV_2021_paper.pdf)] VENet: Voting Enhancement Network for 3D Object Detection. [__`Detection`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Wang_MLVSNet_Multi-Level_Voting_Siamese_Network_for_3D_Visual_Tracking_ICCV_2021_paper.pdf)] MLVSNet: Multi-Level Voting Siamese Network for 3D Visual Tracking.[[code](https://github.com/CodeWZT/MLVSNet)] [__`Tracking`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Liang_Exploring_Geometry-Aware_Contrast_and_Clustering_Harmonization_for_Self-Supervised_3D_Object_ICCV_2021_paper.pdf)] Exploring Geometry-Aware Contrast and Clustering Harmonization for Self-Supervised 3D Object Detection. [__`Detection`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Zhou_TempNet_Online_Semantic_Segmentation_on_Large-Scale_Point_Cloud_Series_ICCV_2021_paper.pdf)] TempNet: Online Semantic Segmentation on Large-scale Point Cloud Series. [__`Segmentation`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Zhang_Perturbed_Self-Distillation_Weakly_Supervised_Large-Scale_Point_Cloud_Semantic_Segmentation_ICCV_2021_paper.pdf)] Perturbed Self-Distillation: Weakly Supervised Large-Scale Point Cloud Semantic Segmentation. [__`Segmentation`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Jiang_Guided_Point_Contrastive_Learning_for_Semi-Supervised_Point_Cloud_Semantic_Segmentation_ICCV_2021_paper.pdf)] Guided Point Contrastive Learning for Semi-Supervised Point Cloud Semantic Segmentation. [__`Segmentation`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Wang_Unsupervised_Point_Cloud_Pre-Training_via_Occlusion_Completion_ICCV_2021_paper.pdf)] Unsupervised Point Cloud Pre-training via Occlusion Completion.[[code](https://github.com/hansen7/OcCo)] [__`training`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Hui_Superpoint_Network_for_Point_Cloud_Oversegmentation_ICCV_2021_paper.pdf)] Superpoint Network for Point Cloud Oversegmentation.[[code](https://github.com/fpthink/SPNet)] [__`Segmentation`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Xu_SGMNet_Learning_Rotation-Invariant_Point_Cloud_Representations_via_Sorted_Gram_Matrix_ICCV_2021_paper.pdf)] SGMNet: Learning Rotation-Invariant Point Cloud Representations via Sorted Gram Matrix. [__`Representations`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Kim_Point_Cloud_Augmentation_With_Weighted_Local_Transformations_ICCV_2021_paper.pdf)] Point Cloud Augmentation with Weighted Local Transformations.[[code](https://github.com/mlvlab/PointWOLF)] [__`Augmentation`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Li_A_Closer_Look_at_Rotation-Invariant_Deep_Point_Cloud_Analysis_ICCV_2021_paper.pdf)] A Closer Look at Rotation-invariant Deep Point Cloud Analysis. [__`Analysis`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Zhao_3DVG-Transformer_Relation_Modeling_for_Visual_Grounding_on_Point_Clouds_ICCV_2021_paper.pdf)] 3DVG-Transformer: Relation Modeling for Visual Grounding on Point Clouds. [__`Visual Grounding`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Hui_Pyramid_Point_Cloud_Transformer_for_Large-Scale_Place_Recognition_ICCV_2021_paper.pdf)] Pyramid Point Cloud Transformer for Large-Scale Place Recognition.[[code](https://github.com/fpthink/PPT-Net)] [__`Recognition`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Liu_LSG-CPD_Coherent_Point_Drift_With_Local_Surface_Geometry_for_Point_ICCV_2021_paper.pdf)] LSG-CPD: Coherent Point Drift with Local Surface Geometry for Point Cloud Registration.[[code](https://github.com/ChirikjianLab/LSG-CPD)] [__`Registration`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Nie_Differentiable_Convolution_Search_for_Point_Cloud_Processing_ICCV_2021_paper.pdf)] Differentiable Convolution Search for Point Cloud Processing. [__`Processing`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Hahner_Fog_Simulation_on_Real_LiDAR_Point_Clouds_for_3D_Object_ICCV_2021_paper.pdf)] Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather.[[code](https://github.com/MartinHahner/LiDAR_fog_sim)] [__`Detection`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Huang_RFNet_Recurrent_Forward_Network_for_Dense_Point_Cloud_Completion_ICCV_2021_paper.pdf)] RFNet: Recurrent Forward Network for Dense Point Cloud Completion. [__`Completion`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Yu_PoinTr_Diverse_Point_Cloud_Completion_With_Geometry-Aware_Transformers_ICCV_2021_paper.pdf)] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers.[[code](https://github.com/yuxumin/PoinTr)] [__`Completion`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Kim_PICCOLO_Point_Cloud-Centric_Omnidirectional_Localization_ICCV_2021_paper.pdf)] PICCOLO: Point Cloud-Centric Omnidirectional Localization. [__`Localization`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Luo_PU-EVA_An_Edge-Vector_Based_Approximation_Solution_for_Flexible-Scale_Point_Cloud_ICCV_2021_paper.pdf)] PU-EVA: An Edge-Vector based Approximation Solution for Flexible-scale Point Cloud Upsampling. [__`Upsampling`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Xiang_A_Backdoor_Attack_Against_3D_Point_Cloud_Classifiers_ICCV_2021_paper.pdf)] A Backdoor Attack Against 3D Point Cloud Classifiers.[[code](https://github.com/zhenxianglance/pcba)] [__`Classification`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Song_Vis2Mesh_Efficient_Mesh_Reconstruction_From_Unstructured_Point_Clouds_of_Large_ICCV_2021_paper.pdf)] Vis2Mesh: Efficient Mesh Reconstruction from Unstructured Point Clouds of Large Scenes with Learned Virtual View Visibility.[[code](https://github.com/GDAOSU/vis2mesh)] [__`Reconstruction`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Zhou_3D_Shape_Generation_and_Completion_Through_Point-Voxel_Diffusion_ICCV_2021_paper.pdf)] 3D Shape Generation and Completion through Point-Voxel Diffusion.[[code](https://alexzhou907.github.io/pvd)] [__`Completion`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Chen_Unsupervised_Learning_of_Fine_Structure_Generation_for_3D_Point_Clouds_ICCV_2021_paper.pdf)] Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projections Matching.[[code](https://github.com/chenchao15/2d_projection_matching)] [__`Generation`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Xu_OMNet_Learning_Overlapping_Mask_for_Partial-to-Partial_Point_Cloud_Registration_ICCV_2021_paper.pdf)] OMNet: Learning Overlapping Mask for Partial-to-Partial Point Cloud Registration.[[code](https://github.com/megvii-research/OMNet)] [__`Registration`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Mazur_Cloud_Transformers_A_Universal_Approach_to_Point_Cloud_Processing_Tasks_ICCV_2021_paper.pdf)] Cloud Transformers: A Universal Approach To Point Cloud Processing Tasks. [__`Transformer`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Zheng_Box-Aware_Feature_Enhancement_for_Single_Object_Tracking_on_Point_Clouds_ICCV_2021_paper.pdf)] Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds.[[code](https://github.com/Ghostish/BAT)] [__`Tracking`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Lee_DeepPRO_Deep_Partial_Point_Cloud_Registration_of_Objects_ICCV_2021_paper.pdf)] DeepPRO: Deep Partial Point Cloud Registration of Objects. [__`Registration`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Xiang_Walk_in_the_Cloud_Learning_Curves_for_Point_Clouds_Shape_ICCV_2021_paper.pdf)] Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis.[[code](https://curvenet.github.io/)] [__`Curves`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Wu_Feature_Interactive_Representation_for_Point_Cloud_Registration_ICCV_2021_paper.pdf)] Feature Interactive Representation for Point Cloud Registration.[[code](https://github.com/Ghostish/BAT)] [__`Tracking`__]
- [[ICCV](openaccess.thecvf.com/content/ICCV2021/papers/Weng_CAPTRA_CAtegory-Level_Pose_Tracking_for_Rigid_and_Articulated_Objects_From_ICCV_2021_paper.pdf)] CAPTRA: CAtegory-Level Pose Tracking for Rigid and Articulated Objects From Point Clouds.[[code](https://yijiaweng.github.io/CAPTRA)] [__`Pose Tracking`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Magnet_DWKS_A_Local_Descriptor_of_Deformations_Between_Meshes_and_Point_ICCV_2021_paper.pdf)] DWKS: A Local Descriptor of Deformations Between Meshes and Point Clouds.[[code](https://github.com/RobinMagnet/DWKS)] [__`Descriptor`__]
- [[ICCV](openaccess.thecvf.com/content/ICCV2021/papers/Jubran_Provably_Approximated_Point_Cloud_Registration_ICCV_2021_paper.pdf)] Provably Approximated Point Cloud Registration. [__`Registration`__]
- [[ICCV](openaccess.thecvf.com/content/ICCV2021/papers/Feng_Free-Form_Description_Guided_3D_Visual_Graph_Network_for_Object_Grounding_ICCV_2021_paper.pdf)] Free-Form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud.[[code](https://github.com/PNXD/FFL-3DOG)] [__`Grounding`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Wu_Feature_Interactive_Representation_for_Point_Cloud_Registration_ICCV_2021_paper.pdf)] Deep Implicit Surface Point Prediction Networks.[[code](https://github.com/Ghostish/BAT)] [__`Tracking`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Min_Distinctiveness_Oriented_Positional_Equilibrium_for_Point_Cloud_Registration_ICCV_2021_paper.pdf)] Distinctiveness oriented Positional Equilibrium for Point Cloud Registration. [__`Registration`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Cao_PCAM_Product_of_Cross-Attention_Matrices_for_Rigid_Registration_of_Point_ICCV_2021_paper.pdf)] PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Clouds. [__`Registration`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Le_CPFN_Cascaded_Primitive_Fitting_Networks_for_High-Resolution_Point_Clouds_ICCV_2021_paper.pdf)] CPFN: Cascaded Primitive Fitting Networks for High-Resolution Point Clouds.[[code](https://github.com/erictuanle/CPFN)] [__`Fitting`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Li_PointBA_Towards_Backdoor_Attacks_in_3D_Point_Cloud_ICCV_2021_paper.pdf)] PointBA: Towards Backdoor Attacks in 3D Point Cloud. [__`Attacks`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Yang_Unsupervised_Point_Cloud_Object_Co-Segmentation_by_Co-Contrastive_Learning_and_Mutual_ICCV_2021_paper.pdf)] Unsupervised Point Cloud Object Co-Segmentation by Co-Contrastive Learning and Mutual Attention Sampling.[[code](https://github.com/jimmy15923/unsup_point_coseg)][__`Segmentation`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Lorenz_Robustness_Certification_for_Point_Cloud_Models_ICCV_2021_paper.pdf)] Robustness Certification for Point Cloud Models.[__`Certification`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Xu_RPVNet_A_Deep_and_Efficient_Range-Point-Voxel_Fusion_Network_for_LiDAR_ICCV_2021_paper.pdf)] RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation.[__`Segmentation`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Kim_Minimal_Adversarial_Examples_for_Deep_Learning_on_3D_Point_Clouds_ICCV_2021_paper.pdf)] Minimal Adversarial Examples for Deep Learning on 3D Point Clouds.[__`Adversarial`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Chen_Shape_Self-Correction_for_Unsupervised_Point_Cloud_Understanding_ICCV_2021_paper.pdf)] Shape Self-Correction for Unsupervised Point Cloud Understanding.[__`Understanding`__]
- [[ICCV](openaccess.thecvf.com/content/ICCV2021/papers/Zhu_AdaFit_Rethinking_Learning-Based_Normal_Estimation_on_Point_Clouds_ICCV_2021_paper.pdf)] AdaFit: Rethinking Learning-Based Normal Estimation on Point Clouds. [[code](https://github.com/Runsong123/AdaFit)] [__`Normal Estimation`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Li_Towards_Efficient_Graph_Convolutional_Networks_for_Point_Cloud_Handling_ICCV_2021_paper.pdf)] Towards Efficient Graph Convolutional Networks for Point Cloud Handling.[__`Graph`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Yuan_InstanceRefer_Cooperative_Holistic_Understanding_for_Visual_Grounding_on_Point_Clouds_ICCV_2021_paper.pdf)] InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds Through Instance Multi-Level Contextual Referring. [[code](https://github.com/CurryYuan/InstanceRefer)] [__`Visual Grounding`__]
- [[ICCV](openaccess.thecvf.com/content/ICCV2021/papers/Zou_Geometry-Aware_Self-Training_for_Unsupervised_Domain_Adaptation_on_Object_Point_Clouds_ICCV_2021_paper.pdf)] Geometry-Aware Self-Training for Unsupervised Domain Adaptation on Object Point Clouds. [[code](https://github.com/zou-longkun/GAST)] [__`Domain Adaptation`__]
- [[ICCV](https://openaccess.thecvf.com/content/ICCV2021/papers/Yang_Progressive_Seed_Generation_Auto-Encoder_for_Unsupervised_Point_Cloud_Learning_ICCV_2021_paper.pdf)] Progressive Seed Generation Auto-Encoder for Unsupervised Point Cloud Learning.[__`Encoder`__]
- [[ICCV](https://zju3dv.github.io/udolo/)] You Don't Only Look Once: Constructing Spatial-Temporal Memory for Integrated 3D Object Detection and Tracking. [[code](https://github.com/zju3dv/UDOLO)] [__`Detection`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2021/html/Ali_RPSRNet_End-to-End_Trainable_Rigid_Point_Set_Registration_Network_Using_Barnes-Hut_CVPR_2021_paper.html)] RPSRNet: End-to-End Trainable Rigid Point Set Registration Network Using Barnes-Hut 2D-Tree Representation [__`reg.`__]
- [[TPAMI](https://doi.org/10.1109/TPAMI.2020.3043769)] Acceleration of Non-Rigid Point Set Registration With Downsampling and Gaussian Process Regression. [__`reg.`__]
- [[TPAMI](https://doi.org/10.1109/TPAMI.2020.2978477)] Point Set Registration for 3D Range Scans Using Fuzzy Cluster-Based Metric and Efficient Global Optimization. [__`reg.`__]
- [[TPAMI](https://doi.org/10.1109/TPAMI.2019.2940655)] Topology-Aware Non-Rigid Point Cloud Registration. [__`reg.`__]
- [[NeurIPS](https://proceedings.neurips.cc/paper/2021/hash/c85b2ea9a678e74fdc8bafe5d0707c31-Abstract.html)] CoFiNet: Reliable Coarse-to-fine Correspondences for Robust PointCloud Registration. [__`reg.`__]
- [[NeurIPS](https://proceedings.neurips.cc/paper/2021/hash/2b0f658cbffd284984fb11d90254081f-Abstract.html)] Accurate Point Cloud Registration with Robust Optimal Transport. [__`reg.`__]
---
## 2022
- [[arXiv](https://arxiv.org/abs/2201.12769)] MVP-Net: Multiple View Pointwise Semantic Segmentation of Large-Scale Point Clouds. [__`Segmentation.`__]
- [[arXiv](https://arxiv.org/abs/2201.12733)] TPC: Transformation-Specific Smoothing for Point Cloud Models. [__`Classification.`__]
- [[arXiv](https://arxiv.org/abs/2201.12296)] Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions. [[code](https://github.com/jiachens/ModelNet40-C)] [__`Classification.`__]
- [[arXiv](https://arxiv.org/abs/2201.11388)] Contrastive Embedding Distribution Refinement and Entropy-Aware Attention for 3D Point Cloud Classification. [[code](https://github.com/YangFengSEU/CEDR)] [__`Classification.`__]
- [[arXiv](https://arxiv.org/abs/2201.12094)] Neighborhood-aware Geometric Encoding Network for Point Cloud Registration. [[code](https://github.com/zhulf0804/NgeNet)] [__`Registration.`__]
- [[arXiv](https://arxiv.org/abs/2202.03377)] Benchmarking and Analyzing Point Cloud Classification under Corruptions. [[code](https://github.com/jiawei-ren/ModelNet-C)] [__`Classification.`__]
- [[arXiv](https://arxiv.org/abs/2202.06688)] Geometric Transformer for Fast and Robust Point Cloud Registration. [[code](https://github.com/qinzheng93/GeoTransformer)] [__`Registration.`__]
- [[arXiv](https://arxiv.org/abs/2202.06028)] OctAttention: Octree-based Large-scale Contexts Model for Point Cloud Compression. [[code](https://github.com/zb12138/OctAttention)] [__`Compression.`__]
-
- [[WACV](https://arxiv.org/abs/2104.11896)] M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers. [[code](https://github.com/rayguan97/M3DETR)] [__`Detection.`__]
-
- [[ICLR](https://arxiv.org/abs/2202.07123)] Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework. [[code](https://github.com/ma-xu/pointMLP-pytorch)] [__`Classification`__]
- [[ICLR](https://arxiv.org/abs/2111.11704)] Deep Point Cloud Reconstruction. [__`Reconstruction.`__]
-
- [[AAAI](https://arxiv.org/abs/2201.01976)] SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection. [[code](https://github.com/blakechen97/SASA)] [__`Detection`__]
-
- [[CVPR](https://arxiv.org/abs/2112.02413)] PointCLIP: Point Cloud Understanding by CLIP. [[code](https://github.com/ZrrSkywalker/PointCLIP)] [__`Understanding`__]
- [[CVPR](https://xharlie.github.io/projects/project_sites/pointnerf/index.html)] Point-NeRF: Point-based Neural Radiance Fields. [[code](https://github.com/Xharlie/pointnerf)] [__`Reconstruction`__]
- [[CVPR](https://arxiv.org/pdf/2203.01509v1.pdf)] SoftGroup for 3D Instance Segmentation on Point Clouds. [[code](https://github.com/thangvubk/SoftGroup)] [__`Segmentation`__]
- [[CVPR](https://arxiv.org/pdf/2203.01730v1.pdf)] Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds. [[code](https://github.com/Ghostish/Open3DSOT)] [__`Tracking`__]
- [[CVPR](https://arxiv.org/pdf/2112.09329.pdf)] Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinders. [__`Fitting`__]
- [[CVPR](https://arxiv.org/abs/2203.00680)] CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding. [[code](https://github.com/MohamedAfham/CrossPoint)] [__`Understanding`__]
- [[CVPR](https://arxiv.org/abs/2203.03888)] ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotation. [[code](https://github.com/robinwang1/ART-Point)] [__`Rotation`__]
- [[CVPR](https://arxiv.org/abs/2203.04041)] Shape-invariant 3D Adversarial Point Clouds. [[code](https://github.com/shikiw/SI-Adv)] [__`Adversarial`__]
- [[CVPR](https://arxiv.org/pdf/2203.05238.pdf)] Back To Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement. [[code](https://github.com/wyf-ACCEPT/BackToReality)] [__`Detection`__]
- [[CVPR](https://arxiv.org/pdf/2203.05272v1.pdf)] Contrastive Boundary Learning for Point Cloud Segmentation. [[code](https://github.com/LiyaoTang/contrastBoundary)] [__`Segmentation`__]
- [[CVPR](https://arxiv.org/pdf/2203.05662v1.pdf)] Point Density-Aware Voxels for LiDAR 3D Object Detection. [[code](https://github.com/TRAILab/PDV)] [__`Detection`__]
- [[CVPR](https://arxiv.org/abs/2203.06558)] AutoGPart: Intermediate Supervision Search for Generalizable 3D Part Segmentation. [__`Segmentation`__]
- [[CVPR](https://arxiv.org/pdf/2203.08195v1.pdf)] DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection. [[code](https://github.com/tensorflow/lingvo/tree/master/lingvo)] [__`Detection`__]
- [[CVPR](https://arxiv.org/pdf/2203.08537v1.pdf)] Scribble-Supervised LiDAR Semantic Segmentation. [[code](https://github.com/ouenal/scribblekitti)] [__`Segmentation`__]
- [[CVPR](https://arxiv.org/abs/2111.14819)] Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling. [[code](https://github.com/lulutang0608/Point-BERT)] [__`BERT`__]
- [[CVPR](https://arxiv.org/pdf/2203.11139v1.pdf)] Not All Points Are Equal: Learning Highly Efficient Point-based Detectorsfor 3D LiDAR Point Clouds. [[code](https://github.com/yifanzhang713/IA-SSD)] [__`Detection`__]
- [[CVPR](https://www4.comp.polyu.edu.hk/~cslzhang/paper/VoxSeT_cvpr22.pdf)] Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds. [[code](https://github.com/skyhehe123/VoxSeT)] [__`Detection`__]
- [[CVPR](https://arxiv.org/pdf/2203.11496v1.pdf)] TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers. [[code](https://github.com/XuyangBai/TransFusion/)] [__`Detection`__]
- [[CVPR](https://arxiv.org/pdf/2203.11590v1.pdf)] IDEA-Net: Dynamic 3D Point Cloud Interpolation via Deep Embedding Alignment. [[code](https://github.com/ZENGYIMING-EAMON/IDEA-Net)] [__`Interpolation`__]
- [[CVPR](https://arxiv.org/pdf/2203.13090v1.pdf)] AziNorm: Exploiting the Radial Symmetry of Point Cloud for Azimuth-Normalized 3D Perception. [[code](https://github.com/hustvl/AziNorm)] [__`Symmetry`__]
- [[CVPR](https://arxiv.org/pdf/2203.12917v1.pdf)] WarpingGAN: Warping Multiple Uniform Priors for Adversarial 3D Point Cloud Generation. [[code](https://github.com/yztang4/WarpingGAN)] [__`Generation`__]
- [[CVPR](https://arxiv.org/pdf/2203.13394v1.pdf)] Point2Seq: Detecting 3D Objects as Sequences. [[code](https://github.com/ocNflag/point2seq)] [__`Detection`__]
- [[CVPR](https://arxiv.org/pdf/2203.14517v1.pdf)] REGTR: End-to-end Point Cloud Correspondences with Transformers. [[code](https://github.com/yewzijian/RegTR)] [__`Registration`__]
- [[CVPR](https://arxiv.org/pdf/2203.14508v1.pdf)] Stratified Transformer for 3D Point Cloud Segmentation. [[code](https://github.com/dvlab-research/Stratified-Transformer)] [__`Segmentation`__]
- [[CVPR](https://arxiv.org/pdf/2203.14486v1.pdf)] Equivariant Point Cloud Analysis via Learning Orientations for Message Passing. [[code](https://github.com/luost26/Equivariant-OrientedMP)] [__`Classification`__]
- [[CVPR](https://arxiv.org/pdf/2203.14453v1.pdf)] SC2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration. [[code](https://github.com/ZhiChen902/SC2-PCR)] [__`Registration`__]
- [[CVPR](https://arxiv.org/pdf/2203.15118v1.pdf)] LiDAR Snowfall Simulation for Robust 3D Object Detection. [[code](https://github.com/SysCV/LiDAR_snow_sim)] [__`Detection`__]
- [[CVPR](https://arxiv.org/pdf/2203.15580v1.pdf)] Learning a Structured Latent Space for Unsupervised Point Cloud Completion. [__`Completion`__]
- [[CVPR](https://arxiv.org/pdf/2203.15125v1.pdf)] Text2Pos: Text-to-Point-Cloud Cross-Modal Localization. [[code](https://text2pos.github.io/)] [__`Localization`__]
- [[CVPR](https://arxiv.org/pdf/2203.09931.pdf)] 3DAC: Learning Attribute Compression for Point Clouds. [__`Compression`__]
- [[CVPR](https://arxiv.org/pdf/2203.11113.pdf)] No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfaces. [[code](https://github.com/jx-zhong-for-academic-purpose/Kinet)] [__`Flow`__]
- [[CVPR](https://arxiv.org/pdf/2204.00325v1.pdf)] CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detection. [__`Detection`__]
- [[CVPR](https://arxiv.org/pdf/2203.16895v1.pdf)] Deformation and Correspondence Aware Unsupervised Synthetic-to-Real Scene Flow Estimation for Point Clouds. [[code](https://github.com/leolyj/DCA-SRSFE)] [__`Flow`__]
- [[CVPR](https://arxiv.org/pdf/2204.02174v1.pdf)] Multi-View Transformer for 3D Visual Grounding. [[code](https://github.com/sega-hsj/MVT-3DVG)] [__`Grounding`__]
- [[CVPR](https://arxiv.org/pdf/2203.15882v1.pdf)] Learning to Detect Mobile Objects from LiDAR Scans Without Labels. [[code](https://github.com/YurongYou/MODEST)] [__`Detection`__]
- [[CVPR](https://arxiv.org/pdf/2204.02251.pdf)] RBGNet: Ray-based Grouping for 3D Object Detection. [[code](https://github.com/Haiyang-W/RBGNet)] [__`Detection`__]
- [[CVPR](https://fengxianghe.github.io/paper/wang2022bridged.pdf)] Bridged Transformer for Vision and Point Cloud 3D Object Detection. [__`Detection`__]
- [[CVPR oral](https://arxiv.org/pdf/2204.06272v1.pdf)] 3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection. [[code](https://github.com/fjhzhixi/3D-SPS)] [__`Visual Grounding`__]
- [[CVPR](https://arxiv.org/pdf/2202.06688.pdf)] Geometric Transformer for Fast and Robust Point Cloud Registration. [[code](https://github.com/qinzheng93/GeoTransformer)] [__`Registration`__]
- [[CVPR](https://arxiv.org/pdf/2112.02857.pdf)] PTTR: Relational 3D Point Cloud Object Tracking with Transformer. [[code](https://github.com/Jasonkks/PTTR)] [__`Tracking`__]
- [[CVPR](https://kovenyu.com/eon/static/yu2022eon.pdf)] Rotationally Equivariant 3D Object Detection. [[code](https://kovenyu.com/eon/)] [__`Detection`__]
- [[CVPR](https://arxiv.org/pdf/2204.12667v1.pdf)] MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation. [[code](https://www.nec-labs.com/~mas/MM-TTA/)] [__`Segmentation`__]
- [[CVPR](https://arxiv.org/pdf/2204.12684v1.pdf)] Density-preserving Deep Point Cloud Compression. [[code](https://github.com/yunhe20/D-PCC)] [__`Compression`__]
- [[CVPR](https://arxiv.org/pdf/2204.05687.pdf)] 3DeformRS: Certifying Spatial Deformations on Point Clouds. [[code](https://github.com/gaperezsa/3DeformRS)] [__`Deformations`__]
- [[CVPR oral](https://arxiv.org/pdf/2205.05740v1.pdf)] Surface Representation for Point Clouds. [[code](https://github.com/hancyran/RepSurf)] [__`Representation`__]
- [[CVPR](https://arxiv.org/pdf/2205.13490v1.pdf)] SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation. [[code](https://github.com/wangzy22/SemAffiNet)] [__`Segmentation`__]
- [[CVPR](https://arxiv.org/abs/2205.11028)] RCP: Recurrent Closest Point for Scene Flow Estimation on 3D Point Clouds. [[code](https://github.com/gxd1994/RCP)] [__`Flow`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Cai_3DJCG_A_Unified_Framework_for_Joint_Dense_Captioning_and_Visual_CVPR_2022_paper.pdf)] 3DJCG: A Unified Framework for Joint Dense Captioning and Visual Grounding on 3D Point Clouds. [__`Grounding`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Tang_Multi-Instance_Point_Cloud_Registration_by_Efficient_Correspondence_Clustering_CVPR_2022_paper.pdf)] Multi-instance Point Cloud Registration by Efficient Correspondence Clustering. [[code](https://github.com/SJTU-ViSYS/multi-instant-reg)] [__`Registration`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Li_Lepard_Learning_Partial_Point_Cloud_Matching_in_Rigid_and_Deformable_CVPR_2022_paper.pdf)] Lepard: Learning partial point cloud matching in rigid and deformable scenes. [[code](https://github.com/rabbityl/lepard)] [__`Matching`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Li_Robust_Structured_Declarative_Classifiers_for_3D_Point_Clouds_Defending_Adversarial_CVPR_2022_paper.pdf)] Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks With Implicit Gradients. [[code](https://zhang-vislab.github.io/)] [__`Attack`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Feng_Neural_Points_Point_Cloud_Representation_With_Neural_Fields_for_Arbitrary_CVPR_2022_paper.pdf)] Neural Points: Point Cloud Representation With Neural Fields for Arbitrary Upsampling. [[code](https://github.com/WanquanF/NeuralPoints)] [__`Upsampling`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Yamada_Point_Cloud_Pre-Training_With_Natural_3D_Structures_CVPR_2022_paper.pdf)] Point Cloud Pre-training with Natural 3D Structures. [[code](https://ryosuke-yamada.github.io/PointCloud-FractalDataBase/)] [__`Pre-training`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Yang_A_Unified_Query-Based_Paradigm_for_Point_Cloud_Understanding_CVPR_2022_paper.pdf)] A Unified Query-based Paradigm for Point Cloud Understanding. [__`Understanding`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Ma_Surface_Reconstruction_From_Point_Clouds_by_Learning_Predictive_Context_Priors_CVPR_2022_paper.pdf)] Surface Reconstruction From Point Clouds by Learning Predictive Context Priors. [[code](https://github.com/mabaorui/PredictableContextPrior)] [__`Reconstruction`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Li_RigidFlow_Self-Supervised_Scene_Flow_Learning_on_Point_Clouds_by_Local_CVPR_2022_paper.pdf)] RigidFlow: Self-Supervised Scene Flow Learning on Point Clouds by Local Rigidity Prior. [__`Flow`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Chen_Deterministic_Point_Cloud_Registration_via_Novel_Transformation_Decomposition_CVPR_2022_paper.pdf)] Deterministic Point Cloud Registration via Novel Transformation Decomposition. [__`Registration`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Lehner_3D-VField_Adversarial_Augmentation_of_Point_Clouds_for_Domain_Generalization_in_CVPR_2022_paper.pdf)] 3D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detection. [[code](https://crashd-cars.github.io/)] [__`Detection`__]
- [[CVPRW](https://openaccess.thecvf.com/content/CVPR2022W/WAD/html/Wang_PointMotionNet_Point-Wise_Motion_Learning_for_Large-Scale_LiDAR_Point_Clouds_Sequences_CVPRW_2022_paper.html)] PointMotionNet: Point-Wise Motion Learning for Large-Scale LiDAR Point Clouds Sequences [__`oth.`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Yang_An_MIL-Derived_Transformer_for_Weakly_Supervised_Point_Cloud_Segmentation_CVPR_2022_paper.pdf)] An MIL-Derived Transformer for Weakly Supervised Point Cloud Segmentation. [[code](https://github.com/jimmy15923/wspss_mil_transformer)] [__`Segmentation`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Chen_Why_Discard_if_You_Can_Recycle_A_Recycling_Max_Pooling_CVPR_2022_paper.pdf)] Why Discard if You Can Recycle?: A Recycling Max Pooling Module for 3D Point Cloud Analysis. [__`Analysis`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Nie_Pyramid_Architecture_for_Multi-Scale_Processing_in_Point_Cloud_Segmentation_CVPR_2022_paper.pdf)] Pyramid Architecture for Multi-Scale Processing in Point Cloud Segmentation. [[code](https://github.com/ginobilinie/kp_pyramid)] [__`Segmentation`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Yu_Finding_Good_Configurations_of_Planar_Primitives_in_Unorganized_Point_Clouds_CVPR_2022_paper.pdf)] Finding Good Configurations of Planar Primitives in Unorganized Point Clouds. [__`Primitives`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Yang_No-Reference_Point_Cloud_Quality_Assessment_via_Domain_Adaptation_CVPR_2022_paper.pdf)] No-Reference Point Cloud Quality Assessment via Domain Adaptation. [[code](https://github.com/Qi-Yangsjtu/IT-PCQA)] [__`Assessment`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Wang_Learning_Local_Displacements_for_Point_Cloud_Completion_CVPR_2022_paper.pdf)] Learning Local Displacements for Point Cloud Completion. [__`Completion`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Xing_Point_Cloud_Color_Constancy_CVPR_2022_paper.pdf)] Point Cloud Color Constancy. [[code](https://github.com/xyxingx/Point-Cloud-Color-Constancy)] [__`Color`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Rotstein_Multimodal_Colored_Point_Cloud_to_Image_Alignment_CVPR_2022_paper.pdf)] Multimodal Colored Point Cloud to Image Alignment. [__`Alignment`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Zhao_Self-Supervised_Arbitrary-Scale_Point_Clouds_Upsampling_via_Implicit_Neural_Representation_CVPR_2022_paper.pdf)] Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation. [[code](https://github.com/xnowbzhao/sapcu)] [__`Upsampling`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Li_LiDARCap_Long-Range_Marker-Less_3D_Human_Motion_Capture_With_LiDAR_Point_CVPR_2022_paper.pdf)] LiDARCap: Long-Range Marker-Less 3D Human Motion Capture With LiDAR Point Clouds. [__`Motion`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Shen_Domain_Adaptation_on_Point_Clouds_via_Geometry-Aware_Implicits_CVPR_2022_paper.pdf)] Domain Adaptation on Point Clouds via Geometry-Aware Implicits. [[code](https://github.com/Jhonve/ImplicitPCDA)] [__`Adaptation`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Shi_Weakly_Supervised_Segmentation_on_Outdoor_4D_Point_Clouds_With_Temporal_CVPR_2022_paper.pdf)] Weakly Supervised Segmentation on Outdoor 4D point clouds with Temporal Matching and Spatial Graph Propagation. [__`Segmentation`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Tang_LAKe-Net_Topology-Aware_Point_Cloud_Completion_by_Localizing_Aligned_Keypoints_CVPR_2022_paper.pdf)] LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypoints. [__`Completion`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Liu_SS3D_Sparsely-Supervised_3D_Object_Detection_From_Point_Cloud_CVPR_2022_paper.pdf)] SS3D: Sparsely-Supervised 3D Object Detection from Point Cloud. [__`Detection`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Pang_Upright-Net_Learning_Upright_Orientation_for_3D_Point_Cloud_CVPR_2022_paper.pdf)] Upright-Net: Learning Upright Orientation for 3D Point Cloud. [__`Orientation`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Ma_Reconstructing_Surfaces_for_Sparse_Point_Clouds_With_On-Surface_Priors_CVPR_2022_paper.pdf)] Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priors. [[code](https://github.com/mabaorui/OnSurfacePrior)] [__`Reconstruction`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Li_HybridCR_Weakly-Supervised_3D_Point_Cloud_Semantic_Segmentation_via_Hybrid_Contrastive_CVPR_2022_paper.pdf)] HybridCR: Weakly-Supervised 3D Point Cloud Semantic Segmentation via Hybrid Contrastive Regularization. [__`Segmentation`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Fan_Self-Supervised_Global-Local_Structure_Modeling_for_Point_Cloud_Domain_Adaptation_With_CVPR_2022_paper.pdf)] Self-Supervised Global-Local Structure Modeling for Point Cloud Domain Adaptation with Reliable Voted Pseudo Labels. [__`Adaptation`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Zheng_Boosting_3D_Object_Detection_by_Simulating_Multimodality_on_Point_Clouds_CVPR_2022_paper.pdf)] Boosting 3D Object Detection by Simulating Multimodality on Point Clouds. [__`Detection`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2022/papers/Ben-Shabat_DiGS_Divergence_Guided_Shape_Implicit_Neural_Representation_for_Unoriented_Point_CVPR_2022_paper.pdf)] DiGS: Divergence Guided Shape Implicit Neural Representation for Unoriented Point Clouds. [[code](https://chumbyte.github.io/DiGS-Site/)] [__`Neural Representations`__]
-
- [[ECCV](https://arxiv.org/abs/2207.01452)] Open-world semantic segmentation for Lidar Point Clouds. [[code](https://github.com/Jun-CEN/Open_world_3D_semantic_segmentation)] [__`Segmentation`__]
- [[ECCV](https://arxiv.org/abs/2207.04397)] 2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds. [[code](https://github.com/yanx27/2DPASS)] [__`Segmentation`__]
- [[ECCV](https://arxiv.org/abs/2207.05317)] CPO: Change Robust Panorama to Point Cloud Localization. [__`Localization`__]
- [[ECCV](http://virtualhumans.mpi-inf.mpg.de/papers/chibane22Box2Mask/Chibane_Box2Mask.pdf)] Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes. [[code](https://virtualhumans.mpi-inf.mpg.de/box2mask/)] [__`Segmentation`__]
- [[ECCV](https://arxiv.org/abs/2203.16001)] Meta-Sampler: Almost-Universal yet Task-Oriented Sampling for Point Clouds. [[code](https://github.com/ttchengab/MetaSampler)] [__`Sampling`__]
- [[ECCV](https://arxiv.org/pdf/2207.07522v1.pdf)] Bi-PointFlowNet: Bidirectional Learning for Point Cloud Based Scene Flow Estimation. [[code](https://github.com/cwc1260/BiFlow)] [__`Scene Flow`__]
- [[ECCV](https://arxiv.org/abs/2203.11183)] Masked Discrimination for Self-Supervised Learning on Point Clouds. [[code](https://github.com/haotian-liu/MaskPoint)] [__`Self-Supervised Learning`__]
- [[ECCV](https://arxiv.org/pdf/2207.11995v1.pdf)] 3D Siamese Transformer Network for Single Object Tracking on Point Clouds. [[code](https://github.com/fpthink/STNet)] [__`Tracking`__]
- [[ECCV](https://arxiv.org/abs/2207.11889)] Salient Object Detection for Point Clouds. [[code](https://git.openi.org.cn/OpenPointCloud/PCSOD)] [__`Detection`__]
- [[ECCV](https://arxiv.org/abs/2207.11753)] Label-Guided Auxiliary Training Improves 3D Object Detector. [[code](https://github.com/FabienCode/LG3D)] [__`Detection`__]
- [[ECCV](https://shengyuh.github.io/eccv22/index.html)] Dynamic 3D Scene Analysis by Point Cloud Accumulation. [[code](https://github.com/prs-eth/PCAccumulation)] [__`Scene`__]
- [[ECCV](https://michaelramamonjisoa.github.io/projects/MonteBoxFinder)] MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud. [[code](https://github.com/MichaelRamamonjisoa/MonteBoxFinder)] [__`Fit`__]
- [[ECCV](https://arxiv.org/pdf/2208.00281v1.pdf)] Point Primitive Transformer for Long-Term 4D Point Cloud Video Understanding. [__`Video Understanding`__]
- [[ECCV](https://arxiv.org/abs/2208.01925)] SuperLine3D: Self-supervised Line Segmentation and Description for LiDAR Point Cloud. [[code](https://github.com/zxrzju/SuperLine3D.git)] [__`Segmentation`__]
- [[ECCV](https://arxiv.org/abs/2208.04043)] SLiDE: Self-supervised LiDAR De-snowing through Reconstruction Difficulty. [__`De-snowing`__]
- [[ECCV](https://arxiv.org/abs/2208.03624)] Graph R-CNN: Towards Accurate 3D Object Detection with Semantic-Decorated Local Graph. [[code](https://github.com/Nightmare-n/GraphRCNN)] [__`Detection`__]
- [[ECCV](https://arxiv.org/abs/2208.05962)] PointTree: Transformation-Robust Point Cloud Encoder with Relaxed K-D Trees. [[code](https://github.com/immortalCO/PointTree)] [__`Encoder`__]
- [[ECCV](https://www.zyrianov.org/lidargen/)] Learning to Generate Realistic LiDAR Point Clouds. [[code](https://www.zyrianov.org/lidargen/)] [__`LiDAR`__]
- [[ECCV](https://link.springer.com/chapter/10.1007/978-3-031-20086-1_39)] FBNet: Feedback Network for Point Cloud Completion. [[code](https://github.com/hikvision-research/3DVision/tree/main/PointCompletion/FBNet)] [__`Completion`__]
- [[ECCV](https://arxiv.org/pdf/2203.16482.pdf)] RFNet-4D: Joint Object Reconstruction and Flow Estimation from 4D Point Clouds. [[code](https://github.com/hkust-vgd/RFNet-4D?utm_source=catalyzex.com)] [__`Flow`__]
- [[ECCV](https://arxiv.org/pdf/2210.08064.pdf)] LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds. [__`Segmentation`__]
- [[ECCV](https://link.springer.com/chapter/10.1007/978-3-031-19842-7_13)] FH-Net: A Fast Hierarchical Network for Scene Flow Estimation on Real-World Point Clouds. [[code](https://github.com/pigtigger/FH-Net)] [__`Flow`__]
- [[ECCV](https://link.springer.com/chapter/10.1007/978-3-031-19769-7_2)] Learning-Based Point Cloud Registration for 6D Object Pose Estimation in the Real World. [[code](https://github.com/Dangzheng/MatchNorm)] [__`Registration`__]
- [[ECCV](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136620485.pdf)] CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinement. [[code](https://github.com/THU-DA-6D-Pose-Group/CATRE)] [__`Registration`__]
- [[ECCV](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136620504.pdf)] Optimization over Disentangled Encoding: Unsupervised Cross-Domain Point Cloud Completion via Occlusion Factor Manipulation. [[code](https://github.com/azuki-miho/OptDE)] [__`Completion`__]
- [[ECCV](https://link.springer.com/chapter/10.1007/978-3-031-20086-1_31)] Unsupervised Learning of 3D Semantic Keypoints with Mutual Reconstruction. [[code](https://github.com/YYYYYHC/Learning-3D-Keypoints-with-Mutual-Recosntruction)] [__`Reconstruction`__]
- [[ECCV](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136620573.pdf)] Revisiting Point Cloud Simplification: A Learnable Feature Preserving Approach. [__`Simplification`__]
- [[ECCV](https://www.ecva.net/papers/eccv_2022/papers_ECCV/papers/136610123.pdf)] Lidar Point Cloud Guided Monocular 3D Object Detection. [[code](https://github.com/SPengLiang/LPCG)] [__`Detection`__]
---
## 2023
- [[CVPR](https://lukemelas.github.io/projection-conditioned-point-cloud-diffusion)] PC2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction. [[code](https://github.com/lukemelas/projection-conditioned-point-cloud-diffusion)] [__`Reconstruction`__]
- [[CVPR](https://arxiv.org/abs/2304.11846)] Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent with Learned Distance Functions. [[code](https://github.com/yunhe20/Grad-PU)] [__`Upsampling`__]
- [[CVPR](https://arxiv.org/abs/2304.09446)] Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection. [[code](https://github.com/WoodwindHu/DTS)] [__`Detection`__]
- [[CVPR](https://arxiv.org/abs/2304.04248)] Curricular Object Manipulation in LiDAR-based Object Detection. [[code](https://github.com/ZZY816/COM)] [__`Detection`__]
- [[CVPR](https://arxiv.org/abs/2303.09950)] Deep Graph-based Spatial Consistency for Robust Non-rigid Point Cloud Registration. [[code](https://github.com/qinzheng93/GraphSCNet)] [__`Registration`__]
- [[CVPR](https://arxiv.org/abs/2303.09950)] BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud Registration. [[code](https://github.com/qinzheng93/GraphSCNet)] [__`Registration`__]
- [[CVPR](https://arxiv.org/abs/2212.06785)] Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders. [[code](https://github.com/ZrrSkywalker/I2P-MAE)] [__`Representations`__]
- [[CVPR](https://arxiv.org/pdf/2303.08134.pdf)] Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis. [[code](https://github.com/ZrrSkywalker/Point-NN)] [__`Representations`__]
- [[CVPR](https://github.com/thu-ml/3D_Corruptions_AD)] Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving. [[code](https://github.com/thu-ml/3D_Corruptions_AD)] [__`Benchmark`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2023/papers/Li_AShapeFormer_Semantics-Guided_Object-Level_Active_Shape_Encoding_for_3D_Object_Detection_CVPR_2023_paper.pdf)] AShapeFormer: Semantics-Guided Object-Level Active Shape Encoding for 3D Object Detection via Transformers. [[code](https://github.com/ZechuanLi/AShapeFormer)] [__`Detection`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2023/html/Xu_CXTrack_Improving_3D_Point_Cloud_Tracking_With_Contextual_Information_CVPR_2023_paper.html)] CXTrack: Improving 3D Point Cloud Tracking With Contextual Information. [__`Tracking`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2023/html/Zheng_NeuralPCI_Spatio-Temporal_Neural_Field_for_3D_Point_Cloud_Multi-Frame_Non-Linear_CVPR_2023_paper.html)] NeuralPCI: Spatio-Temporal Neural Field for 3D Point Cloud Multi-Frame Non-Linear Interpolation. [[code](https://github.com/ispc-lab/NeuralPCI)] [__`Interpolation`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2023/html/Wu_Spatiotemporal_Self-Supervised_Learning_for_Point_Clouds_in_the_Wild_CVPR_2023_paper.html)] Spatiotemporal Self-Supervised Learning for Point Clouds in the Wild. [[code](https://github.com/YanhaoWu/STSSL)] [__`Understanding`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2023/html/Zhang_Frequency-Modulated_Point_Cloud_Rendering_With_Easy_Editing_CVPR_2023_paper.html)] Frequency-Modulated Point Cloud Rendering With Easy Editing. [[code](https://github.com/yizhangphd/FreqPCR)] [__`Nerf`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2023/html/Deng_SE-ORNet_Self-Ensembling_Orientation-Aware_Network_for_Unsupervised_Point_Cloud_Shape_Correspondence_CVPR_2023_paper.html)] SE-ORNet: Self-Ensembling Orientation-Aware Network for Unsupervised Point Cloud Shape Correspondence. [__`Correspondence`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2023/html/Zhang_Hyperspherical_Embedding_for_Point_Cloud_Completion_CVPR_2023_paper.html)] Hyperspherical Embedding for Point Cloud Completion. [__`Completion`__]
- [[CVPR](https://openaccess.thecvf.com/content/CVPR2023/html/He_MSF_Motion-Guided_Sequential_Fusion_for_Efficient_3D_Object_Detection_From_CVPR_2023_paper.html)] MSF: Motion-Guided Sequential Fusion for Efficient 3D Object Detection From Point Cloud Sequences. [[code](https://github.com/skyhehe123/MSF)] [__`Detection`__]
-
- [[ICCV](https://arxiv.org/pdf/2308.07546v1.pdf)] 3DHacker: Spectrum-based Decision Boundary Generation for Hard-label 3D Point Cloud Attack. [__`Attack`__]
- [[ICCV](https://arxiv.org/pdf/2308.06635v1.pdf)] 3DMOTFormer: Graph Transformer for Online 3D Multi-Object Tracking. [[code](https://github.com/dsx0511/3DMOTFormer)] [__`Tracking`__]
- [[ICCV](https://arxiv.org/pdf/2308.06383v1.pdf)] U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Clouds. [[code](https://github.com/ZhangCYG/U-RED)] [__`Retrieval`__]
- [[ICCV](https://arxiv.org/pdf/2308.05667v1.pdf)] 2D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Clouds. [[code](https://github.com/minhaolee/2D3DMATR)] [__`Registration`__]
- [[ICCV](https://arxiv.org/pdf/2308.05438v1.pdf)] Deep Fusion Transformer Network with Weighted Vector-Wise
Keypoints Voting for Robust 6D Object Pose Estimation. [[code](https://github.com/junzastar/DFTr_Voting)] [__`Pose`__]
- [[ICCV](https://arxiv.org/abs/2211.14710)] 3DPPE: 3D Point Positional Encoding for Multi-Camera 3D Object Detection Transformers. [[code](https://github.com/drilistbox/3DPPE)] [__`Detection`__]
- [[ICCV](https://arxiv.org/abs/2308.08140)] GPA-3D: Geometry-aware Prototype Alignment for Unsupervised Domain Adaptive 3D Object Detection from Point Clouds. [[code](https://github.com/Liz66666/GPA3D)] [__`Detection`__]
- [[ICCV](https://arxiv.org/abs/2307.14726)] P2C: Self-Supervised Point Cloud Completion from Single Partial Clouds. [[code](https://github.com/CuiRuikai/Partial2Complete)] [__`Completion`__]
- [[ICCV](https://arxiv.org/abs/2308.05410)] SC3K: Self-supervised and Coherent 3D Keypoints Estimation from Rotated, Noisy, and Decimated Point Cloud Data. [[code](https://github.com/IIT-PAVIS/SC3K)] [__`Keypoints`__]
```diff
- Datasets
```
- [[KITTI](http://www.cvlibs.net/datasets/kitti/)] The KITTI Vision Benchmark Suite. [__`det.`__]
- [[ModelNet](http://modelnet.cs.princeton.edu/)] The Princeton ModelNet . [__`cls.`__]
- [[ShapeNet](https://www.shapenet.org/)] A collaborative dataset between researchers at Princeton, Stanford and TTIC. [__`seg.`__]
- [[PartNet](https://shapenet.org/download/parts)] The PartNet dataset provides fine grained part annotation of objects in ShapeNetCore. [__`seg.`__]
- [[PartNet](http://kevinkaixu.net/projects/partnet.html)] PartNet benchmark from Nanjing University and National University of Defense Technology. [__`seg.`__]
- [[S3DIS](http://buildingparser.stanford.edu/dataset.html#Download)] The Stanford Large-Scale 3D Indoor Spaces Dataset. [__`seg.`__]
- [[ScanNet](http://www.scan-net.org/)] Richly-annotated 3D Reconstructions of Indoor Scenes. [__`cls.`__ __`seg.`__]
- [[Stanford 3D](https://graphics.stanford.edu/data/3Dscanrep/)] The Stanford 3D Scanning Repository. [__`reg.`__]
- [[UWA Dataset](http://staffhome.ecm.uwa.edu.au/~00053650/databases.html)] . [__`cls.`__ __`seg.`__ __`reg.`__]
- [[Princeton Shape Benchmark](http://shape.cs.princeton.edu/benchmark/)] The Princeton Shape Benchmark.
- [[SYDNEY URBAN OBJECTS DATASET](http://www.acfr.usyd.edu.au/papers/SydneyUrbanObjectsDataset.shtml)] This dataset contains a variety of common urban road objects scanned with a Velodyne HDL-64E LIDAR, collected in the CBD of Sydney, Australia. There are 631 individual scans of objects across classes of vehicles, pedestrians, signs and trees. [__`cls.`__ __`match.`__]
- [[ASL Datasets Repository(ETH)](https://projects.asl.ethz.ch/datasets/doku.php?id=home)] This site is dedicated to provide datasets for the Robotics community with the aim to facilitate result evaluations and comparisons. [__`cls.`__ __`match.`__ __`reg.`__ __`det`__]
- [[Large-Scale Point Cloud Classification Benchmark(ETH)](http://www.semantic3d.net/)] This benchmark closes the gap and provides a large labelled 3D point cloud data set of natural scenes with over 4 billion points in total. [__`cls.`__]
- [[Robotic 3D Scan Repository](http://asrl.utias.utoronto.ca/datasets/3dmap/)] The Canadian Planetary Emulation Terrain 3D Mapping Dataset is a collection of three-dimensional laser scans gathered at two unique planetary analogue rover test facilities in Canada.
- [[Radish](http://radish.sourceforge.net/)] The Robotics Data Set Repository (Radish for short) provides a collection of standard robotics data sets.
- [[IQmulus & TerraMobilita Contest](http://data.ign.fr/benchmarks/UrbanAnalysis/#)] The database contains 3D MLS data from a dense urban environment in Paris (France), composed of 300 million points. The acquisition was made in January 2013. [__`cls.`__ __`seg.`__ __`det.`__]
- [[Oakland 3-D Point Cloud Dataset](http://www.cs.cmu.edu/~vmr/datasets/oakland_3d/cvpr09/doc/)] This repository contains labeled 3-D point cloud laser data collected from a moving platform in a urban environment.
- [[Robotic 3D Scan Repository](http://kos.informatik.uni-osnabrueck.de/3Dscans/)] This repository provides 3D point clouds from robotic experiments，log files of robot runs and standard 3D data sets for the robotics community.
- [[Ford Campus Vision and Lidar Data Set](http://robots.engin.umich.edu/SoftwareData/Ford)] The dataset is collected by an autonomous ground vehicle testbed, based upon a modified Ford F-250 pickup truck.
- [[The Stanford Track Collection](https://cs.stanford.edu/people/teichman/stc/)] This dataset contains about 14,000 labeled tracks of objects as observed in natural street scenes by a Velodyne HDL-64E S2 LIDAR.
- [[PASCAL3D+](http://cvgl.stanford.edu/projects/pascal3d.html)] Beyond PASCAL: A Benchmark for 3D Object Detection in the Wild. [__`pos.`__ __`det.`__]
- [[3D MNIST](https://www.kaggle.com/daavoo/3d-mnist)] The aim of this dataset is to provide a simple way to get started with 3D computer vision problems such as 3D shape recognition. [__`cls.`__]
- [[WAD](http://wad.ai/2019/challenge.html)] [[ApolloScape](http://apolloscape.auto/tracking.html)] The datasets are provided by Baidu Inc. [__`tra.`__ __`seg.`__ __`det.`__]
- [[nuScenes](https://d3u7q4379vrm7e.cloudfront.net/object-detection)] The nuScenes dataset is a large-scale autonomous driving dataset.
- [[PreSIL](https://uwaterloo.ca/waterloo-intelligent-systems-engineering-lab/projects/precise-synthetic-image-and-lidar-presil-dataset-autonomous)] Depth information, semantic segmentation (images), point-wise segmentation (point clouds), ground point labels (point clouds), and detailed annotations for all vehicles and people. [[paper](https://arxiv.org/abs/1905.00160)] [__`det.`__ __`aut.`__]
- [[3D Match](http://3dmatch.cs.princeton.edu/)] Keypoint Matching Benchmark, Geometric Registration Benchmark, RGB-D Reconstruction Datasets. [__`reg.`__ __`rec.`__ __`oth.`__]
- [[BLVD](https://github.com/VCCIV/BLVD)] (a) 3D detection, (b) 4D tracking, (c) 5D interactive event recognition and (d) 5D intention prediction. [[ICRA 2019 paper](https://arxiv.org/abs/1903.06405v1)] [__`det.`__ __`tra.`__ __`aut.`__ __`oth.`__]
- [[PedX](https://arxiv.org/abs/1809.03605)] 3D Pose Estimation of Pedestrians, more than 5,000 pairs of high-resolution (12MP) stereo images and LiDAR data along with providing 2D and 3D labels of pedestrians. [[ICRA 2019 paper](https://arxiv.org/abs/1809.03605)] [__`pos.`__ __`aut.`__]
- [[H3D](https://usa.honda-ri.com/H3D)] Full-surround 3D multi-object detection and tracking dataset. [[ICRA 2019 paper](https://arxiv.org/abs/1903.01568)] [__`det.`__ __`tra.`__ __`aut.`__]
- [[Argoverse BY ARGO AI]](https://www.argoverse.org/) Two public datasets (3D Tracking and Motion Forecasting) supported by highly detailed maps to test, experiment, and teach self-driving vehicles how to understand the world around them.[[CVPR 2019 paper](http://openaccess.thecvf.com/content_CVPR_2019/html/Chang_Argoverse_3D_Tracking_and_Forecasting_With_Rich_Maps_CVPR_2019_paper.html)][__`tra.`__ __`aut.`__]
- [[Matterport3D](https://niessner.github.io/Matterport/)] RGB-D: 10,800 panoramic views from 194,400 RGB-D images. Annotations: surface reconstructions, camera poses, and 2D and 3D semantic segmentations. Keypoint matching, view overlap prediction, normal prediction from color, semantic segmentation, and scene classification. [[3DV 2017 paper](https://arxiv.org/abs/1709.06158)] [[code](https://github.com/niessner/Matterport)] [[blog](https://matterport.com/blog/2017/09/20/announcing-matterport3d-research-dataset/)]
- [[SynthCity](https://arxiv.org/abs/1907.04758)] SynthCity is a 367.9M point synthetic full colour Mobile Laser Scanning point cloud. Nine categories. [__`seg.`__ __`aut.`__]
- [[Lyft Level 5](https://level5.lyft.com/dataset/?source=post_page)] Include high quality, human-labelled 3D bounding boxes of traffic agents, an underlying HD spatial semantic map. [__`det.`__ __`seg.`__ __`aut.`__]
- [[SemanticKITTI](http://semantic-kitti.org)] Sequential Semantic Segmentation, 28 classes, for autonomous driving. All sequences of KITTI odometry labeled. [[ICCV 2019 paper](https://arxiv.org/abs/1904.01416)] [__`seg.`__ __`oth.`__ __`aut.`__]
- [[NPM3D](http://npm3d.fr/paris-lille-3d)] The Paris-Lille-3D has been produced by a Mobile Laser System (MLS) in two different cities in France (Paris and Lille). [__`seg.`__]
- [[The Waymo Open Dataset](https://waymo.com/open/)] The Waymo Open Dataset is comprised of high resolution sensor data collected by Waymo self-driving cars in a wide variety of conditions. [__`det.`__]
- [[A*3D: An Autonomous Driving Dataset in Challeging Environments](https://github.com/I2RDL2/ASTAR-3D)] A*3D: An Autonomous Driving Dataset in Challeging Environments. [__`det.`__]
- [[PointDA-10 Dataset](https://github.com/canqin001/PointDAN)] Domain Adaptation for point clouds.
- [[Oxford Robotcar](https://robotcar-dataset.robots.ox.ac.uk/)] The dataset captures many different combinations of weather, traffic and pedestrians. [__`cls.`__ __`det.`__ __`rec.`__]
- [[WHU-TLS BENCHMARK](http://3s.whu.edu.cn/ybs/en/benchmark.htm)] WHU-TLS benchmark dataset. [__`reg.`__]
- [[DALES](https://arxiv.org/abs/2004.11985)] DALES: A Large-scale Aerial LiDAR Data Set for Semantic Segmentation. [__`seg.`__]