https://github.com/yinyunie/3D-Shape-Analysis-Paper-List
A list of recent papers, libraries and datasets about 3D shape/scene analysis (by topics, updating).
https://github.com/yinyunie/3D-Shape-Analysis-Paper-List
3d-detection 3d-reconstruction 3d-representation scene-reconstruction scene-understanding shape-analysis shape-completion
Last synced: about 1 year ago
JSON representation
A list of recent papers, libraries and datasets about 3D shape/scene analysis (by topics, updating).
- Host: GitHub
- URL: https://github.com/yinyunie/3D-Shape-Analysis-Paper-List
- Owner: yinyunie
- Created: 2019-12-31T11:25:25.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2023-12-05T22:22:08.000Z (over 2 years ago)
- Last Synced: 2024-10-28T07:42:23.131Z (over 1 year ago)
- Topics: 3d-detection, 3d-reconstruction, 3d-representation, scene-reconstruction, scene-understanding, shape-analysis, shape-completion
- Language: Python
- Homepage:
- Size: 1.04 MB
- Stars: 945
- Watchers: 81
- Forks: 113
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-ai-list-guide - 3D-Shape-Analysis-Paper-List
README
# 3D-Shape-Analysis-Paper-List
A list of papers, libraries and datasets I recently read is collected for anyone who shows interest at
---
- [3D Detection & Segmentation](#3d-detection--segmentation)
- [Shape Representation](#shape-representation)
- [Shape & Scene Completion](#shape--scene-completion)
- [Shape Reconstruction & Generation](#shape-reconstruction--generation)
- [3D Scene Understanding](#3d-scene-understanding)
- [3D Scene Reconstruction & Generation](#3d-scene-reconstruction--generation)
- [NeRF](#nerf)
- [About Human Body](#about-human-body)
- [General Methods](#general-methods)
- [Others (inc. Networks in Classification, Matching, Registration, Alignment, Depth, Normal, Pose, Keypoints, etc.)](#others-inc-networks-in-classification-matching-registration-alignment-depth-normal-pose-keypoints-etc)
- [Survey, Resources and Tools](#survey-resources-and-tools)
---
Statistics: :fire: code is available & stars >= 100 | :star: citation >= 50
## 3D Detection & Segmentation
- [[Arxiv](https://arxiv.org/abs/2304.06906)] Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding [[Project](https://github.com/microsoft/Swin3D)]
- [[Arxiv](https://arxiv.org/abs/2304.00962)] RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding [[Project](https://jihanyang.github.io/projects/RegionPLC)]
- [[CVPR2023](https://arxiv.org/abs/2303.15440)] EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervision [[Project](https://www.cis.upenn.edu/~leijh/projects/efem/)]
- [[CVPR2023](https://arxiv.org/abs/2303.08129)] PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection [[Project](https://github.com/BLVLab/PiMAE)]
- [[Arxiv](https://arxiv.org/abs/2210.03105)] Mask3D for 3D Semantic Instance Segmentation [[github](https://github.com/JonasSchult/Mask3D)]
- [[ECCV2022](https://arxiv.org/abs/2207.06985)] ObjectBox: From Centers to Boxes for Anchor-Free Object Detection [[github](https://github.com/MohsenZand/ObjectBox)]
- [[Arxiv](https://arxiv.org/abs/2207.00531)] Masked Autoencoders for Self-Supervised Learning on Automotive Point Clouds
- [[CVPR2022](https://arxiv.org/abs/2204.05599)] HyperDet3D: Learning a Scene-conditioned 3D Object Detector
- [[Arxiv](https://arxiv.org/abs/2201.06493v1)] AutoAlign: Pixel-Instance Feature Aggregation for Multi-Modal 3D Object Detection
#### Before 2022
- [[AAAI2022](https://arxiv.org/abs/2112.09205v1)] AFDetV2: Rethinking the Necessity of the Second Stage for Object Detection from Point Clouds
- [[AAAI2022](https://arxiv.org/abs/2112.07241v1)] Static-Dynamic Co-Teaching for Class-Incremental 3D Object Detection
- [[NeurIPS2021](https://arxiv.org/abs/2112.07787v1)] Revisiting 3D Object Detection From an Egocentric Perspective
- [[Arxiv](https://arxiv.org/abs/2112.06375v1)] Embracing Single Stride 3D Object Detector with Sparse Transformer [[github](https://github.com/TuSimple/SST)]
- [[AAAI2022](https://arxiv.org/abs/2112.04628v1)] Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection
- [[Arxiv](https://arxiv.org/abs/2112.04764v1)] 3D-VField: Learning to Adversarially Deform Point Clouds for Robust 3D Object Detection
- [[Arxiv](https://arxiv.org/abs/2112.04702v1)] Fast Point Transformer
- [[3DV2021](https://arxiv.org/abs/2112.01135v1)] Open-set 3D Object Detection
- [[Arxiv](https://arxiv.org/abs/2112.00322v1)] FCAF3D: Fully Convolutional Anchor-Free 3D Object Detection [[Project](https://github.com/samsunglabs/fcaf3d)]
- [[TPAMI2021](https://arxiv.org/abs/2111.15210v1)] Point Cloud Instance Segmentation with Semi-supervised Bounding-Box Mining
- [[Arxiv](https://arxiv.org/abs/2111.12728v1)] Online Adaptation for Implicit Object Tracking and Shape Reconstruction in the Wild
- [[Arxiv](https://arxiv.org/abs/2111.09515v1)] RAANet: Range-Aware Attention Network for LiDAR-based 3D Object Detection with Auxiliary Density Level Estimation [[github](https://github.com/anonymous0522/RAAN)]
- [[Arxiv](https://arxiv.org/abs/2111.09621v1)] SimpleTrack: Understanding and Rethinking 3D Multi-object Tracking [[github](https://github.com/TuSimple/SimpleTrack)]
- [[NeurIPS2021](https://arxiv.org/abs/2111.06881v1)] Multimodal Virtual Point 3D Detection [[Project](https://tianweiy.github.io/mvp/)]
- [[BMVC2021](https://arxiv.org/abs/2110.14921v1)] 3D Object Tracking with Transformer [[github](https://github.com/3bobo/lttr)]
- [[3DV2021](https://arxiv.org/abs/2110.11325v1)] Learning 3D Semantic Segmentation with only 2D Image Supervision
- [[3DV2021](https://arxiv.org/abs/2110.09936v1)] NeuralDiff: Segmenting 3D objects that move in egocentric videos [[Project](https://www.robots.ox.ac.uk/~vadim/neuraldiff/)]
- [[BMVC2021](https://arxiv.org/abs/2110.09355v1)] FAST3D: Flow-Aware Self-Training for 3D Object Detectors
- [[ICCV2021](https://arxiv.org/abs/2110.08188v1)] Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation
- [[CORL2021](https://arxiv.org/abs/2110.06922v1)] DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries [[github](https://github.com/WangYueFt/detr3d)]
- [[NeurIPS2021](https://arxiv.org/abs/2110.06923v1)] Object DGCNN: 3D Object Detection using Dynamic Graphs [[github](https://github.com/WangYueFt/detr3d)]
- [[Arxiv](https://arxiv.org/abs/2110.06049v1)] Improved Pillar with Fine-grained Feature for 3D Object Detection
- [[Arxiv](https://arxiv.org/abs/2110.02531v1)] 3D-FCT: Simultaneous 3D Object Detection and Tracking Using Feature Correlation
- [[ICCVW2021](https://arxiv.org/abs/2110.00464v1)] MonoCInIS: Camera Independent Monocular 3D Object Detection using Instance Segmentation
- [[Arxiv](https://arxiv.org/abs/2109.11835v1)] GSIP: Green Semantic Segmentation of Large-Scale Indoor Point Clouds
- [[Arxiv](https://arxiv.org/abs/2109.10852v1)] Pix2seq: A Language Modeling Framework for Object Detection
- [[Arxiv](https://arxiv.org/abs/2109.10473v1)] MVM3Det: A Novel Method for Multi-view Monocular 3D Detection
- [[ICCV2021](https://arxiv.org/abs/2109.04456v1)] NEAT: Neural Attention Fields for End-to-End Autonomous Driving [[github](https://github.com/autonomousvision/neat)]
- [[ICCV2021](https://arxiv.org/abs/2109.02499v1)] Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection
- [[ICCV2021](https://arxiv.org/abs/2109.01066v1)] 4D-Net for Learned Multi-Modal Alignment
- [[ICCV2021](https://arxiv.org/abs/2103.16130)] Active Learning for Deep Object Detection via Probabilistic Modeling [[github](https://github.com/nvlabs/al-mdn)]
- [[ICCV2021](https://arxiv.org/abs/2109.08141)] An End-to-End Transformer Model for 3D Object Detection [[Project](https://facebookresearch.github.io/3detr/)]
- [[ICCV2021](https://arxiv.org/abs/2108.10723)] Improving 3D Object Detection with Channel-wise Transformer
- [[ICCV2021](https://arxiv.org/abs/2109.02497)] Voxel Transformer for 3D Object Detection
- [[CVPR2021](https://openaccess.thecvf.com/content/CVPR2021/papers/Chai_To_the_Point_Efficient_3D_Object_Detection_in_the_Range_CVPR_2021_paper.pdf)] To the Point: Efficient 3D Object Detection in the Range Image With Graph Convolution Kernels
- [[Arxiv](https://arxiv.org/abs/2104.11896)] M3DeTR: Multi-representation, Multi-scale, Mutual-relation 3D Object Detection with Transformers
- [[ICCV2021](https://arxiv.org/abs/2108.10312v1)] Exploring Simple 3D Multi-Object Tracking for Autonomous Driving
- [[ICCV2021](https://arxiv.org/abs/2108.08258v1)] LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector
- [[ICCV2021](https://arxiv.org/abs/2108.07478v1)] Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks [[github](https://github.com/Gorilla-Lab-SCUT/SSTNet)]
- [[ICCV2021](https://arxiv.org/abs/2108.07794v1)] RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detection
- [[ICCV2021](https://arxiv.org/abs/2108.06417v1)] Is Pseudo-Lidar needed for Monocular 3D Object detection?
- [[IROS2021](https://arxiv.org/abs/2108.06455v1)] PTT: Point-Track-Transformer Module for 3D Single Object Tracking in Point Clouds [[github](https://github.com/shanjiayao/PTT)]
- [[ICCV2021](https://arxiv.org/abs/2108.05699v1)] Oriented R-CNN for Object Detection [[github](https://github.com/jbwang1997/OBBDetection)]
- [[ICCV2021](https://arxiv.org/abs/2108.04728v1)] Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds [[github](https://github.com/Ghostish/BAT)]
- [[IROS2021](https://arxiv.org/abs/2108.04602v1)] Joint Multi-Object Detection and Tracking with Camera-LiDAR Fusion for Autonomous Driving
- [[ACMMM2021](https://arxiv.org/abs/2108.03648v1)] From Voxel to Point: IoU-guided 3D Object Detection for Point Cloud with Voxel-to-Point Decoder [[github](https://github.com/jialeli1/From-Voxel-to-Point)]
- [[ICCV2021](https://arxiv.org/abs/2108.04023v1)] DRINet: A Dual-Representation Iterative Learning Network for Point Cloud Segmentation
- [[ICCV2021](https://arxiv.org/abs/2108.02350v1)] Hierarchical Aggregation for 3D Instance Segmentation [[github](https://github.com/hustvl/HAIS)]
- [[Arxiv](https://arxiv.org/abs/2108.00620v1)] Investigating Attention Mechanism in 3D Point Cloud Object Detection [[pytorch](https://github.com/ShiQiu0419/attentions_in_3D_detection)]
- [[ICCV2021](https://arxiv.org/abs/2107.13824v1)] VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation [[pytorch](https://github.com/hzykent/VMNet)]
- [[ICCV2021](https://arxiv.org/abs/2107.13774v1)] Geometry Uncertainty Projection Network for Monocular 3D Object Detection
- [[Arxiv](https://arxiv.org/abs/2107.13269v1)] Aug3D-RPN: Improving Monocular 3D Object Detection by Synthetic Images with Virtual Depth
- [[Arxiv](https://arxiv.org/abs/2107.12707v1)] DV-Det: Efficient 3D Point Cloud Object Detection with Dynamic Voxelization
- [[ICCV2021](https://arxiv.org/abs/2107.11769v1)] ReDAL: Region-based and Diversity-aware Active Learning for Point Cloud Semantic Segmentation
- [[ICCV2021](https://arxiv.org/abs/2107.11669)] Rank & Sort Loss for Object Detection and Instance Segmentation [[pytorch](https://github.com/kemaloksuz/RankSortLoss)]
- [[Arxiv](https://arxiv.org/abs/2107.04013v1)] Multi-Modality Task Cascade for 3D Object Detection [[github](https://github.com/Divadi/MTC_RCNN)]
- [[ACMMM2021](https://arxiv.org/abs/2107.02493v1)] Neighbor-Vote: Improving Monocular 3D Object Detection through Neighbor Distance Voting
- [[Arxiv](https://arxiv.org/abs/2106.15796v1)] Monocular 3D Object Detection: An Extrinsic Parameter Free Approach
- [[Arxiv](https://arxiv.org/pdf/2106.14101v1.pdf)] Real-time 3D Object Detection using Feature Map Flow [[pytorch](https://github.com/YoushaaMurhij/FMFNet)]
- [[Arxiv](https://arxiv.org/pdf/2106.13381v1.pdf)] To the Point: Efficient 3D Object Detection in the Range Image with Graph Convolution Kernels
- [[CVPR2021](https://arxiv.org/abs/2106.13365v1)] RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection
- [[Arxiv](https://arxiv.org/abs/2106.06882v1)] Sparse PointPillars: Exploiting Sparsity in Birds-Eye-View Object Detection
- [[Arxiv](https://arxiv.org/abs/2106.01178)] ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection [[Project](https://github.com/saic-vul/imvoxelnet)]
- [[CVPR2021](https://arxiv.org/pdf/2105.06461.pdf)] 3D Spatial Recognition without Spatially Labeled 3D [[Project](https://facebookresearch.github.io/WyPR/)]
- [[Arxiv](https://arxiv.org/abs/2105.00268)] Lite-FPN for Keypoint-based Monocular 3D Object Detection
- [[TPAMI](https://arxiv.org/abs/2104.08797)] MonoGRNet: A General Framework for Monocular 3D Object Detection
- [[Arxiv](https://arxiv.org/abs/2104.09035)] Lidar Point Cloud Guided Monocular 3D Object Detection
- [[Arxiv](https://arxiv.org/pdf/2104.05858.pdf)] Geometry-aware data augmentation for monocular 3D object detection
- [[Arxiv](https://arxiv.org/abs/2104.06041)] OCM3D: Object-Centric Monocular 3D Object Detection
- [[CVPR2021](https://arxiv.org/abs/2104.02323v1)] Objects are Different: Flexible Monocular 3D Object Detection [[github](https://github.com/zhangyp15/MonoFlex)]
- [[CVPR2021](https://arxiv.org/abs/2104.00902v1)] HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detection
- [[Arxiv](https://arxiv.org/pdf/2104.00678v1.pdf)] Group-Free 3D Object Detection via Transformers
[[pytorch](https://github.com/zeliu98/Group-Free-3D)]
- [[CVPR2021](https://arxiv.org/pdf/2103.17202v1.pdf)] GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection [[pytorch](https://github.com/abhi1kumar/groomed_nms)]
- [[CVPR2021](https://arxiv.org/pdf/2104.06114.pdf)] Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds [[pytorch](https://github.com/cheng052/BRNet)]
- [[CVPR2021](https://arxiv.org/pdf/2103.16470v1.pdf)] Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection [[github](https://github.com/fudan-zvg/DDMP)]
- [[CVPR2021](https://arxiv.org/pdf/2103.16237v1.pdf)] Delving into Localization Errors for Monocular 3D Object Detection [[github](https://github.com/xinzhuma/monodle)]
- [[CVPR2021](https://arxiv.org/pdf/2103.16054v1.pdf)] 3D-MAN: 3D Multi-frame Attention Network for Object Detection
- [[CVPR2021](https://arxiv.org/pdf/2103.15297v1.pdf)] LiDAR R-CNN: An Efficient and Universal 3D Object Detector [[github](https://github.com/tusimple/LiDAR_RCNN)]
- [[CVPR2021](https://arxiv.org/pdf/2012.04355v2.pdf)] 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection [[pytorch](https://github.com/THU17cyz/3DIoUMatch)]
- [[CVPR2021](https://arxiv.org/pdf/2103.13164v1.pdf)] M3DSSD: Monocular 3D Single Stage Object Detector
- [[CVPR2021](https://arxiv.org/abs/2103.12605v2)] MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation
- [[Arxiv](https://arxiv.org/pdf/2103.10042.pdf)] SparsePoint: Fully End-to-End Sparse 3D Object Detector
- [[Arxiv](https://arxiv.org/abs/2103.10039)] RangeDet:In Defense of Range View for LiDAR-based 3D Object Detection
- [[ICRA2021](https://arxiv.org/abs/2103.09422)] YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection [[github](https://github.com/Owen-Liuyuxuan/visualDet3D)]
- [[CVPR2021](https://arxiv.org/pdf/2103.05346v1.pdf)] ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection [[github](https://github.com/CVMI-Lab/ST3D)]
- [[Arxiv](https://arxiv.org/pdf/2103.05073v1.pdf)] Offboard 3D Object Detection from Point Cloud Sequences
- [[CVPR2021](https://arxiv.org/abs/2011.13328v2)] DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution [[github](https://github.com/aim-uofa/DyCo3D)]
- [[Arxiv](https://arxiv.org/pdf/2103.02093.pdf)] Pseudo-labeling for Scalable 3D Object Detection
- [[Arxiv](https://arxiv.org/pdf/2102.03747.pdf)] DPointNet: A Density-Oriented PointNet for 3D Object Detection in Point Clouds
- [[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)]
- [[Arxiv](https://arxiv.org/pdf/2101.11952v1.pdf)] Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
- [[Arxiv](https://arxiv.org/pdf/2006.04080v2.pdf)] CubifAE-3D: Monocular Camera Space Cubification for Auto-Encoder based
3D Object Detection
- [[Arxiv](https://arxiv.org/pdf/2101.02672.pdf)] Self-Attention Based Context-Aware 3D Object Detection [[pytorch](https://github.com/AutoVision-cloud/SA-Det3D)]
- [[Arxiv](https://arxiv.org/pdf/2012.15712.pdf)] Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection
#### Before 2021
- [[Arxiv](https://arxiv.org/pdf/2012.03121.pdf)] It’s All Around You: Range-Guided Cylindrical Network for 3D Object Detection
- [[Arxiv](https://arxiv.org/pdf/2012.04355.pdf)] 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection [[Project](https://thu17cyz.github.io/3DIoUMatch/)]
- [[Arxiv](https://arxiv.org/pdf/2012.05796.pdf)] Demystifying Pseudo-LiDAR for Monocular 3D Object Detection
- [[3DV2020](https://arxiv.org/pdf/2012.09418.pdf)] PanoNet3D: Combining Semantic and Geometric Understanding for LiDAR Point Cloud Detection
- [[AAAI2021](https://arxiv.org/pdf/2012.10412.pdf)] PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection
- [[Arxiv](https://arxiv.org/pdf/2012.10217.pdf)] SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation
- [[Arxiv](https://arxiv.org/pdf/2012.11409.pdf)] 3D Object Detection with Pointformer
- [[WACV2021](https://arxiv.org/pdf/2011.04841.pdf)] CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection [[pytorch](https://github.com/mrnabati/CenterFusion)]
- [[Arxiv](https://arxiv.org/pdf/2011.10033.pdf)] Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation [[pytorch](https://github.com/xinge008/Cylinder3D)]
- [[Arxiv](https://arxiv.org/pdf/2011.09977.pdf)] Learning to Predict the 3D Layout of a Scene
- [[Arxiv](https://arxiv.org/pdf/2011.12001.pdf)] Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes [[Project](https://github.com/qq456cvb/CanonicalVoting)]
- [[Arxiv](https://arxiv.org/pdf/2011.13328.pdf)] DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution
- [[Arxiv](https://arxiv.org/abs/2011.13628)] Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving
- [[NeurIPS2020](https://proceedings.neurips.cc/paper/2020/file/f2fc990265c712c49d51a18a32b39f0c-Paper.pdf)] Every View Counts: Cross-View Consistency in 3D Object Detection with Hybrid-Cylindrical-Spherical Voxelization
- [[NeurIPS2020](https://papers.nips.cc/paper/2020/file/9b72e31dac81715466cd580a448cf823-Paper.pdf)] Group Contextual Encoding for 3D Point Clouds [[pytorch](https://github.com/AsahiLiu/PointDetectron)]
- [[Arxiv](https://arxiv.org/pdf/2010.16279.pdf)] 3D Object Recognition By Corresponding and Quantizing Neural 3D Scene Representations [[Project](https://mihirp1998.github.io/project_pages/3dq/)]
- [[Arxiv](https://arxiv.org/pdf/2009.05307.pdf)] A Density-Aware PointRCNN for 3D Objection Detection in Point Clouds
- [[Arxiv](https://arxiv.org/abs/2009.00764)] Monocular 3D Detection with Geometric Constraints Embedding and Semi-supervised Training
- [[ECCV2020](https://arxiv.org/pdf/2008.13748.pdf)] Reinforced Axial Refinement Network for Monocular 3D Object Detection
- [[Arxiv](https://arxiv.org/pdf/2006.01250.pdf)] RUHSNet: 3D Object Detection Using Lidar Data in Real Time [[pytorch](https://github.com/abhinavsagar/ruhsnet)]
- [[IROS2020](http://www.xinshuoweng.com/papers/AB3DMOT/camera_ready.pdf)] 3D Multi-Object Tracking: A Baseline and New Evaluation Metrics [[Project](http://www.xinshuoweng.com/projects/AB3DMOT/)][[Code](https://github.com/xinshuoweng/AB3DMOT)]
- [[ECCV2020](https://arxiv.org/pdf/2007.13138.pdf)] Virtual Multi-view Fusion for 3D Semantic Segmentation
- [[ACMMM2020](https://arxiv.org/pdf/2007.13970.pdf)] Weakly Supervised 3D Object Detection from Point Clouds
- [[ECCV2020](https://arxiv.org/abs/2007.11901)] Weakly Supervised 3D Object Detection from Lidar Point Cloud [[pytorch](https://github.com/hlesmqh/WS3D)]
- [[ECCV2020](https://arxiv.org/abs/2007.09548)] Kinematic 3D Object Detection in Monocular Video
- [[IROS2020](https://arxiv.org/pdf/2007.09836.pdf)] Object-Aware Centroid Voting for Monocular 3D Object Detection
- [[ECCV2020](https://arxiv.org/pdf/2007.10323.pdf)] Pillar-based Object Detection for Autonomous Driving
- [[Arxiv](https://arxiv.org/pdf/2007.02099.pdf)] Local Grid Rendering Networks for 3D Object Detection in Point Clouds
- [[Arxiv](https://arxiv.org/pdf/2006.01250.pdf)] Learning to Detect 3D Objects from Point Clouds in Real Time
- [[Arxiv](https://arxiv.org/pdf/2006.04043.pdf)] SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds
- [[CVPR2020](http://openaccess.thecvf.com/content_CVPR_2020/html/Jiang_PointGroup_Dual-Set_Point_Grouping_for_3D_Instance_Segmentation_CVPR_2020_paper.html)] PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
- [[CVPR2020](https://arxiv.org/pdf/2005.05125.pdf)] FroDO: From Detections to 3D Objects
- [[CVPR2020](https://arxiv.org/pdf/2004.00543.pdf)] Physically Realizable Adversarial Examples for LiDAR Object Detection
- [[CVPR2020](https://arxiv.org/pdf/2006.04356.pdf)] Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection
- [[CVPR2020](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
- [[CVPR2020](https://arxiv.org/pdf/2003.00504.pdf)] MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships
- [[CVPR2020](http://openaccess.thecvf.com/content_CVPR_2020/papers/He_Structure_Aware_Single-Stage_3D_Object_Detection_From_Point_Cloud_CVPR_2020_paper.pdf)] Structure Aware Single-stage 3D Object Detection from Point Cloud
- [[CVPR2020](https://arxiv.org/pdf/1912.04799.pdf)] Learning Depth-Guided Convolutions for Monocular 3D Object Detection [[pytorch](https://github.com/dingmyu/D4LCN)] :fire:
- [[CVPR2020](https://arxiv.org/pdf/1912.04986.pdf)] What You See is What You Get: Exploiting Visibility for 3D Object Detection
- [[CVPR2020](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
- [[CVPR2020](https://arxiv.org/pdf/2004.03572.pdf)] Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation
- [[CVPR2020](https://arxiv.org/pdf/2004.03080.pdf)] End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection
- [[CVPR2020](https://arxiv.org/pdf/1912.13192.pdf)] PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
- [[CVPR2020](https://arxiv.org/pdf/2004.05679.pdf)] MLCVNet: Multi-Level Context VoteNet for 3D Object Detection
- [[CVPR2020](https://arxiv.org/pdf/1911.10150.pdf)] PointPainting: Sequential Fusion for 3D Object Detection
- [[CVPR2020](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
- [[CVPR2020](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)]
- [[CVPR2020](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
- [[CVPR2020](https://arxiv.org/pdf/2003.00186.pdf)] HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection
- [[CVPR2020](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
- [[Arxiv](https://arxiv.org/pdf/2006.05682.pdf)] H3DNet: 3D Object Detection Using Hybrid Geometric Primitives [[pytorch](https://github.com/zaiweizhang/H3DNet)]
- [[CVPR2020](https://arxiv.org/pdf/2005.13888.pdf)] P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds
- [[Arxiv](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
- [[CVPR2020](https://arxiv.org/pdf/2004.09305.pdf)] Joint Spatial-Temporal Optimization for Stereo 3D Object Tracking
- [[CVPR2020](https://arxiv.org/pdf/2004.08745.pdf)] Learning to Evaluate Perception Models Using Planner-Centric Metrics
- [[CVPR2020](https://arxiv.org/pdf/2004.03572.pdf)] Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation [[pytorch](https://github.com/zju3dv/disprcnn)]
- [[Arxiv](https://arxiv.org/pdf/2004.02774.pdf)] SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds [[github](https://github.com/xinge008/SSN)]
- [[CVPR2020](https://arxiv.org/pdf/2004.03080.pdf)] End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection [[github](https://github.com/mileyan/pseudo-LiDAR_e2e)]
- [[Arxiv](https://arxiv.org/pdf/2004.02693.pdf)] Finding Your (3D) Center: 3D Object Detection Using a Learned Loss
- [[CVPR2020](https://arxiv.org/pdf/2004.01658.pdf)] PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
- [[CVPR2020](https://arxiv.org/pdf/2003.13867.pdf)] 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segm
- [[CVPR2020](https://arxiv.org/pdf/2003.06233.pdf)] Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation
- [[CVPR2020](https://arxiv.org/pdf/2003.06537.pdf)] OccuSeg: Occupancy-aware 3D Instance Segmentation
- [[CVPR2020](https://arxiv.org/pdf/2003.05593.pdf)] Learning to Segment 3D Point Clouds in 2D Image Space
- [[CVPR2020](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)]
- [[AAAI2020](https://arxiv.org/pdf/2003.00529.pdf)] ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection
- [[Arxiv](https://arxiv.org/pdf/2003.00504.pdf)] MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships
- [[Arxiv](https://arxiv.org/pdf/2003.00186.pdf)] HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection
- [[Arxiv](https://arxiv.org/pdf/2002.10111.pdf)] SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation
- [[Arxiv](https://arxiv.org/pdf/2002.10187.pdf)] 3DSSD: Point-based 3D Single Stage Object Detector
- [[Arxiv](https://arxiv.org/pdf/2002.01619.pdf)] Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimation
- [[CVPR2020](https://arxiv.org/pdf/2001.10692.pdf)] ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votes
- [[Arxiv](https://arxiv.org/pdf/2001.10609.pdf)] A Review on Object Pose Recovery: from 3D Bounding Box Detectors to Full 6D Pose Estimators
- [[Arxiv](https://arxiv.org/pdf/1912.08830.pdf)] ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language
- [[Arxiv](https://arxiv.org/pdf/1904.07850.pdf)] Objects as Points [[github](https://github.com/xingyizhou/CenterNet)] :star::fire:
- [[Arxiv](https://arxiv.org/pdf/2001.03343.pdf)] RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving [[github](https://github.com/Banconxuan/RTM3D)]
- [[CVPR2020](https://arxiv.org/pdf/2001.03398.pdf)] DSGN: Deep Stereo Geometry Network for 3D Object Detection [[github](https://github.com/chenyilun95/DSGN)]
- [[Arxiv](https://arxiv.org/pdf/2001.01349.pdf)] Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation
- [[Arxiv](https://arxiv.org/pdf/1912.13192.pdf)] PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
- [[Arxiv](https://arxiv.org/pdf/1912.12791.pdf)] Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots
- [[CVPR2020](https://arxiv.org/pdf/1912.11803.pdf)] SESS: Self-Ensembling Semi-Supervised 3D Object Detection
- [[NeurIPS2019](https://papers.nips.cc/paper/9093-perspectivenet-3d-object-detection-from-a-single-rgb-image-via-perspective-points)] PerspectiveNet: 3D Object Detection from a Single RGB Image via Perspective Points
- [[NeurIPS2019](https://arxiv.org/pdf/1906.01140.pdf)] Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds
- [[ICCV2019](http://openaccess.thecvf.com/content_ICCV_2019/papers/Qi_Deep_Hough_Voting_for_3D_Object_Detection_in_Point_Clouds_ICCV_2019_paper.pdf)] Deep Hough Voting for 3D Object Detection in Point Clouds
- [[AAAI2020](https://arxiv.org/pdf/1912.09654.pdf)] JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds
- [[ICCV2019](http://openaccess.thecvf.com/content_ICCV_2019/papers/Brazil_M3D-RPN_Monocular_3D_Region_Proposal_Network_for_Object_Detection_ICCV_2019_paper.pdf)] M3D-RPN: Monocular 3D Region Proposal Network for Object Detection [[pytorch](https://github.com/garrickbrazil/M3D-RPN)]
- [[ICCV2019](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
- [[Arxiv](https://arxiv.org/pdf/1912.08035.pdf)] Single-Stage Monocular 3D Object Detection with Virtual Cameras
- [[Arxiv](https://arxiv.org/pdf/1912.10336.pdf)] Depth Completion via Deep Basis Fitting
- [[Arxiv](https://arxiv.org/pdf/1912.00202.pdf)] Relation Graph Network for 3D Object Detection in Point Clouds
- [[CVPR2019](https://arxiv.org/pdf/1812.07003.pdf)] 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans [[pytorch](https://github.com/Sekunde/3D-SIS)] :fire:
- [[ICCV2019](http://openaccess.thecvf.com/content_ICCV_2019/papers/Halber_Rescan_Inductive_Instance_Segmentation_for_Indoor_RGBD_Scans_ICCV_2019_paper.pdf)] Rescan: Inductive Instance Segmentation for Indoor RGBD Scans [[C++](https://github.com/mhalber/Rescan)]
- [[ICCV2019](http://openaccess.thecvf.com/content_ICCV_2019/papers/Tang_Transferable_Semi-Supervised_3D_Object_Detection_From_RGB-D_Data_ICCV_2019_paper.pdf)] Transferable Semi-Supervised 3D Object Detection From RGB-D Data
- [[ICCV2019](http://openaccess.thecvf.com/content_ICCV_2019/papers/Yang_STD_Sparse-to-Dense_3D_Object_Detector_for_Point_Cloud_ICCV_2019_paper.pdf)] STD: Sparse-to-Dense 3D Object Detector for Point Cloud
- [[CVPR2019](https://arxiv.org/pdf/1812.04244.pdf)] PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud [[pytorch](https://github.com/sshaoshuai/PointRCNN)]
- [[Arxiv](https://arxiv.org/pdf/1908.02990.pdf)] Fast Point R-CNN
- [[Arxiv](https://arxiv.org/pdf/1908.09492.pdf)] Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection [[pytorch](https://github.com/poodarchu/Det3D)] :fire:
- [[ECCV2018](https://arxiv.org/pdf/1803.10409.pdf)] 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation [[pytorch](https://github.com/angeladai/3DMV)] :fire:
---
## Shape Representation
- [[CVPR2023](https://arxiv.org/abs/2303.14191v1)] Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning [[github](https://github.com/Pointcept/Pointcept)]
- [[Arxiv](https://arxiv.org/abs/2303.04341)] Neural Vector Fields: Implicit Representation by Explicit Learning
- [[ECCV2022](https://arxiv.org/abs/2207.11911)] NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editing [[Project](https://zju3dv.github.io/neumesh/)]
- [[Arxiv](https://arxiv.org/abs/2207.01545)] Masked Autoencoders in 3D Point Cloud Representation Learning
- [[Arxiv](https://arxiv.org/abs/2206.05837v1)] NeuralODF: Learning Omnidirectional Distance Fields for 3D Shape Representation
- [[Siggraph2022](https://arxiv.org/abs/2202.08345)] Learning Smooth Neural Functions via Lipschitz Regularization [[Project](https://nv-tlabs.github.io/lip-mlp/)]
- [[Siggraph2022](https://arxiv.org/abs/2205.02825)] Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representations [[Project](https://wang-ps.github.io/dualocnn)]
- [[Arxiv](https://arxiv.org/abs/2204.07159)] A Level Set Theory for Neural Implicit Evolution under Explicit Flows
- [[CVPR2022](https://arxiv.org/abs/2204.07126)] GIFS: Neural Implicit Function for General Shape Representation [[Project](https://jianglongye.com/gifs/)]
- [[Arxiv](https://arxiv.org/abs/2202.04713v1)] PINs: Progressive Implicit Networks for Multi-Scale Neural Representations
- [[Arxiv](https://arxiv.org/abs/2202.04241v1)] Distillation with Contrast is All You Need for Self-Supervised Point Cloud Representation Learning
- [[Arxiv](https://arxiv.org/abs/2202.02444v1)] Spelunking the Deep: Guaranteed Queries for General Neural Implicit Surfaces
- [[Arxiv](https://arxiv.org/abs/2202.03532)] MINER: Multiscale Implicit Neural Representations
- [[Arxiv](https://arxiv.org/abs/2201.02279v1)] De-rendering 3D Objects in the Wild
- [[Arxiv](https://arxiv.org/abs/2201.00785v1)] Implicit Autoencoder for Point Cloud Self-supervised Representation Learning
#### Before 2022
- [[Arxiv](https://arxiv.org/abs/2112.10196v1)] End-to-End Learning of Multi-category 3D Pose and Shape Estimation
- [[Arxiv](https://arxiv.org/abs/2112.09329v1)] Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinders
- [[Arxiv](https://arxiv.org/abs/2112.05300v1)] Representing 3D Shapes with Probabilistic Directed Distance Fields
- [[Arxiv](https://arxiv.org/abs/2112.03221v1)] Text2Mesh: Text-Driven Neural Stylization for Meshes [[Project](https://threedle.github.io/text2mesh/)]
- [[Arxiv](https://arxiv.org/abs/2112.02413v1)] PointCLIP: Point Cloud Understanding by CLIP [[github](https://github.com/ZrrSkywalker/PointCLIP)]
- [[Arxiv](https://arxiv.org/abs/2111.15363v1)] Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding
- [[Arxiv](https://arxiv.org/abs/2111.13652v1)] Gradient-SDF: A Semi-Implicit Surface Representation for 3D Reconstruction
- [[Arxiv](https://arxiv.org/abs/2111.12488v1)] Intuitive Shape Editing in Latent Space
- [[NeurIPS2021](https://arxiv.org/abs/2111.07117v1)] Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views [[github](https://github.com/NanboLi/MulMON)]
- [[Arxiv](https://arxiv.org/abs/2111.13674)] Neural Fields as Learnable Kernels for 3D Reconstruction
- [[NeurIPS2021](https://arxiv.org/abs/2111.01067v1)] OctField: Hierarchical Implicit Functions for 3D Modeling [[github](https://github.com/IGLICT/OctField)]
- [[3DV2021](https://arxiv.org/abs/2110.11036v1)] RefRec: Pseudo-labels Refinement via Shape Reconstruction for Unsupervised 3D Domain Adaptation [[github](https://github.com/CVLAB-Unibo/RefRec)]
- [[3DV2021](https://arxiv.org/abs/2110.07882v1)] PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation [[Project](https://arxiv.org/pdf/2110.07882v1.pdf)]
- [[Arxiv](https://arxiv.org/abs/2112.04645)] BACON: Band-limited Coordinate Networks for Multiscale Scene Representation [[Project](https://davidlindell.com/publications/bacon)]
- [[Arxiv](https://arxiv.org/abs/2112.05381)] UNIST: Unpaired Neural Implicit Shape Translation Network [[Project](https://qiminchen.github.io/unist/)]
- [[Arxiv](https://arxiv.org/abs/2109.01605v1)] Representing Shape Collections with Alignment-Aware Linear Models [[Project](https://romainloiseau.github.io/deep-linear-shapes/)]
- [[ICCV2021](https://arxiv.org/abs/2109.00179v1)] Spatio-temporal Self-Supervised Representation Learning for 3D Point Clouds
- [[Arxiv](https://arxiv.org/abs/2111.09383?context=cs.GR)] DeepCurrents: Learning Implicit Representations of Shapes with Boundaries
- [[3DV](https://arxiv.org/abs/2110.11860)] AIR-Nets: An Attention-Based Framework for Locally Conditioned Implicit Representations [[github](https://github.com/SimonGiebenhain/AIR-Nets)]
- [[Arxiv](https://arxiv.org/abs/2110.05770)] HyperCube: Implicit Field Representations of Voxelized 3D Models
- [[Arxiv](https://arxiv.org/abs/2108.09432v1)] ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generators
- [[ICCV2021](https://arxiv.org/abs/2109.05591)] Multiresolution Deep Implicit Functions for 3D Shape Representation
- [[ICCV2021](https://arxiv.org/abs/2108.04628v1)] Learning Canonical 3D Object Representation for Fine-Grained Recognition
- [[Arxiv](https://arxiv.org/abs/2108.02104v1)] Point Discriminative Learning for Unsupervised Representation Learning on 3D Point Clouds
- [[Arxiv](https://arxiv.org/abs/2107.11024)] A Deep Signed Directional Distance Function for Object Shape Representation
- [[Arxiv](https://arxiv.org/abs/2107.04004v1)] 3D Neural Scene Representations for Visuomotor Control [[Project](https://3d-representation-learning.github.io/nerf-dy/)]
- [[Arxiv](https://arxiv.org/pdf/2104.07645.pdf)] A-SDF: Learning Disentangled Signed Distance Functions
for Articulated Shape Representation [[Project](https://jitengmu.github.io/A-SDF/)]
- [[Arxiv](https://arxiv.org/abs/2104.06392)] ShapeMOD: Macro Operation Discovery for 3D Shape Programs [[Project](https://rkjones4.github.io/shapeMOD.html)]
- [[Arxiv](https://arxiv.org/pdf/2104.03851v1.pdf)] CoCoNets: Continuous Contrastive 3D Scene Representations [[Project](https://mihirp1998.github.io/project_pages/coconets/)]
- [[Arxiv](https://arxiv.org/abs/2102.09105)] DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes with Biharmonic Coordinates [[Project](https://github.com/Colin97/DeepMetaHandles)]
#### Before 2021
- [[CVPR2021](http://campar.in.tum.de/pub/paetzold2021cldice/paetzold2021cldice.pdf)] clDice-a Novel Topology-Preserving Loss Function for Tubular Structure Segmentation [[github](https://github.com/jocpae/clDice)]
- [[CVPR2021](https://arxiv.org/pdf/2012.00230.pdf)] Point2Skeleton: Learning Skeletal Representations from Point Clouds [[pytorch](https://github.com/clinplayer/Point2Skeleton)]
- [[Arxiv](https://arxiv.org/pdf/2012.03028.pdf)] ParaNet: Deep Regular Representation for 3D Point Clouds
- [[Arxiv](https://arxiv.org/pdf/2012.05657.pdf)] Geometric Adversarial Attacks and Defenses on 3D Point Clouds [[tensorflow](https://github.com/itailang/geometric_adv)]
- [[Arxiv](https://arxiv.org/pdf/2012.07290.pdf)] Learning Category-level Shape Saliency via Deep Implicit Surface Networks
- [[Arxiv](https://arxiv.org/pdf/2012.00926.pdf)] pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis
- [[Arxiv](https://arxiv.org/pdf/2011.14565.pdf)] Deep Implicit Templates for 3D Shape Representation
- [[NeurIPS2020](https://proceedings.neurips.cc/paper/2020/file/731c83db8d2ff01bdc000083fd3c3740-Paper.pdf)] MetaSDF: Meta-learning Signed Distance Functions [[Project](https://vsitzmann.github.io/metasdf/)]
- [[Arxiv](https://arxiv.org/abs/2010.00973)] RISA-Net: Rotation-Invariant Structure-Aware Network for Fine-Grained 3D Shape Retrieval [[tensorflow](https://github.com/IGLICT/RisaNET)]
- [[Arxiv](https://arxiv.org/abs/2009.09808)] Overfit Neural Networks as a Compact Shape Representation
- [[Arxiv](https://arxiv.org/abs/2008.05440)] DSM-Net: Disentangled Structured Mesh Net for Controllable Generation of Fine Geometry [[Project](http://geometrylearning.com/dsm-net/)]
- [[Arxiv](https://arxiv.org/pdf/2008.01639.pdf)] PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations
- [[Arxiv](https://arxiv.org/pdf/2008.02792.pdf)] CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations
- [[Arxiv](https://arxiv.org/pdf/2008.03875.pdf)] ROCNET: RECURSIVE OCTREE NETWORK FOR EFFICIENT 3D DEEP REPRESENTATION
- [[ECCV2020](https://arxiv.org/pdf/2008.04852.pdf)] GeLaTO: Generative Latent Textured Objects [[Project](https://gelato-paper.github.io/)]
- [[ECCV2020](https://arxiv.org/abs/2007.13393)] Ladybird: Quasi-Monte Carlo Sampling for Deep Implicit Field Based 3D Reconstruction with Symmetry
- [[Arxiv](https://arxiv.org/pdf/2007.11571.pdf)] Neural Sparse Voxel Fields
- [[CVPR2020](https://arxiv.org/pdf/2004.09995.pdf)] StructEdit: Learning Structural Shape Variations [[github](https://github.com/hyzcn/structedit)]
- [[Arxiv](https://arxiv.org/pdf/2004.09995.pdf)] PAI-GCN: Permutable Anisotropic Graph Convolutional Networks for 3D Shape Representation Learning [[github](https://github.com/Gaozhongpai/PaiConvMesh)]
- [[CVPR2020](https://arxiv.org/pdf/2004.03028.pdf)] Learning Generative Models of Shape Handles [[Project page](http://mgadelha.me/shapehandles/)]
- [[CVPR2020](https://arxiv.org/pdf/2004.02869.pdf)] DualSDF: Semantic Shape Manipulation using a Two-Level Representation [[github](https://github.com/zekunhao1995/DualSDF)]
- [[CVPR2020](https://arxiv.org/pdf/2004.01176.pdf)] Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image [[pytorch](https://github.com/paschalidoud/hierarchical_primitives)]
- [[NeurIPS2019](https://arxiv.org/pdf/1906.01618.pdf)] Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations [[pytorch](https://github.com/vsitzmann/scene-representation-networks)]
- [[Arxiv](https://arxiv.org/pdf/2003.13834.pdf)] Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions
- [[Arxiv](https://arxiv.org/pdf/2003.12971.pdf)] Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds
- [[Arxiv](https://arxiv.org/pdf/2003.10983.pdf)] Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction
- [[Arxiv](https://arxiv.org/pdf/2003.05559.pdf)] SeqXY2SeqZ: Structure Learning for 3D Shapes by Sequentially Predicting 1D Occupancy Segments From 2D Coordinates
- [[CVPR2020](https://arxiv.org/pdf/2003.03164.pdf)] D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
- [[Arxiv](https://arxiv.org/pdf/2002.10099.pdf)] Implicit Geometric Regularization for Learning Shapes
- [[Arxiv](https://arxiv.org/pdf/2002.06597.pdf)] Analytic Marching: An Analytic Meshing Solution from Deep Implicit Surface Networks
- [[Arxiv](https://arxiv.org/pdf/2002.00349.pdf)] Adversarial Generation of Continuous Implicit Shape Representations [[pytorch](https://github.com/marian42/shapegan)]
- [[Arxiv](https://arxiv.org/pdf/2001.02823.pdf)] A Novel Tree-structured Point Cloud Dataset For Skeletonization Algorithm Evaluation [[dataset](https://github.com/liujiboy/TreePointCloud)]
- [[CVPRW2019](http://openaccess.thecvf.com/content_CVPRW_2019/papers/SkelNetOn/Demir_SkelNetOn_2019_Dataset_and_Challenge_on_Deep_Learning_for_Geometric_CVPRW_2019_paper.pdf)] SkelNetOn 2019: Dataset and Challenge on Deep Learning for Geometric Shape Understanding [[project](http://ubee.enseeiht.fr/skelneton/)]
- [[Arxiv](https://arxiv.org/pdf/1912.11932.pdf)] Skeleton Extraction from 3D Point Clouds by Decomposing the Object into Parts
- [[Arxiv](https://arxiv.org/pdf/1912.11606.pdf)] InSphereNet: a Concise Representation and Classification Method for 3D Object
- [[Arxiv](https://arxiv.org/pdf/1912.06126v1.pdf)] Deep Structured Implicit Functions
- [[CVIU](https://reader.elsevier.com/reader/sd/pii/S1077314218303606?token=0CC172174E5193815DEF57234C50AD55CFA60AAB3672EAC166AEFF051C2021E08D78D78CC1A4716A2317128070FF756C)] 3D articulated skeleton extraction using a single consumer-grade depth camera
- [[ICLR2019](https://arxiv.org/pdf/1810.05795.pdf)] Point Cloud GAN [[tensorflow](https://github.com/chunliangli/Point-Cloud-GAN)]
- [[ICCV2019](http://openaccess.thecvf.com/content_ICCV_2019/papers/Genova_Learning_Shape_Templates_With_Structured_Implicit_Functions_ICCV_2019_paper.pdf)] Learning Shape Templates with Structured Implicit Functions
- [[ICCV2019](http://openaccess.thecvf.com/content_ICCV_2019/papers/Shu_3D_Point_Cloud_Generative_Adversarial_Network_Based_on_Tree_Structured_ICCV_2019_paper.pdf)] 3D Point Cloud Generative Adversarial Network Based on
Tree Structured Graph Convolutions [[pytorch](https://github.com/seowok/TreeGAN)]
- [[ICCV2019](http://openaccess.thecvf.com/content_ICCV_2019/papers/Michalkiewicz_Implicit_Surface_Representations_As_Layers_in_Neural_Networks_ICCV_2019_paper.pdf)] Implicit Surface Representations as Layers in Neural Networks
- [[CVPR2019](http://openaccess.thecvf.com/content_CVPR_2019/papers/Park_DeepSDF_Learning_Continuous_Signed_Distance_Functions_for_Shape_Representation_CVPR_2019_paper.pdf)] DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation [[pytorch](https://github.com/facebookresearch/DeepSDF)] :fire: :star:
- [[SIGGRAPH2019](https://arxiv.org/pdf/1908.00575.pdf)] StructureNet: Hierarchical Graph Networks for 3D Shape Generation [[pytorch](https://github.com/daerduoCarey/structurenet)]
- [[SIGGRAPH Asia2019](https://arxiv.org/pdf/1903.10170.pdf)] LOGAN: Unpaired Shape Transform in Latent Overcomplete Space [[tensorflow](https://github.com/kangxue/LOGAN)]
- [[TOG](https://www.researchgate.net/profile/Yajie_Yan2/publication/326726499_Voxel_cores_efficient_robust_and_provably_good_approximation_of_3D_medial_axes/links/5b7712cd4585151fd11b316a/Voxel-cores-efficient-robust-and-provably-good-approximation-of-3D-medial-axes.pdf)] Voxel Cores: Efficient, robust, and provably good approximation of 3D medial axes
- [[SIGGRAPH2018](https://arxiv.org/pdf/1803.09263.pdf)] P2P-NET: Bidirectional Point Displacement Net for Shape Transform [[tensorflow](https://github.com/kangxue/P2P-NET)]
- [[ICML2018](https://arxiv.org/pdf/1707.02392.pdf)] Learning Representations and Generative Models for 3D Point Clouds [[tensorflow](https://github.com/optas/latent_3d_points)] :fire::star:
- [[NeurIPS2018](https://arxiv.org/pdf/1807.03146.pdf)] Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning [[tensorflow](https://github.com/tensorflow/models/tree/master/research/keypointnet)][[project page](https://keypointnet.github.io/)]:star::fire:
- [[AAAI2018](http://graphics.cs.uh.edu/wp-content/papers/2018/2018-AAAI-SkeletonExtractionFromDepthCamera.pdf)] Unsupervised Articulated Skeleton Extraction from Point Set Sequences Captured by a Single Depth Camera
- [[3DV2018](https://arxiv.org/pdf/1808.01337.pdf)] Parsing Geometry Using Structure-Aware Shape Templates
- [[SIGGRAPH2017](https://www.cse.iitb.ac.in/~sidch/docs/siggraph2017_grass.pdf)] GRASS: Generative Recursive Autoencoders for Shape Structures [[pytorch](https://github.com/junli-lj/Grass)] :fire:
- [[TOG](https://pdfs.semanticscholar.org/cc9a/2d7aff3a4238812c29e7d7525b4e4794fffc.pdf)] Erosion Thickness on Medial Axes of 3D Shapes
- [[Vis Comput](https://link.springer.com/content/pdf/10.1007%2Fs00371-016-1331-z.pdf)] Distance field guided L1-median skeleton extraction
- [[CGF](https://onlinelibrary.wiley.com/doi/pdf/10.1111/cgf.13098)] Contracting Medial Surfaces Isotropically for Fast Extraction of Centred Curve Skeletons
- [[CGF](https://onlinelibrary.wiley.com/doi/pdf/10.1111/cgf.13570)] Improved Use of LOP for Curve Skeleton Extraction
- [[SIGGRAPH Asia2015](https://boris.unibe.ch/81116/1/dpoints.pdf)] Deep Points Consolidation [[C++ & Qt](https://www.dropbox.com/s/hroijgjajj4cadi/point-cloud-processing-vs2013-201908.zip?dl=0)]
- [[SIGGRAPH2015](https://dl.acm.org/doi/pdf/10.1145/2787626.2792658)] Burning The Medial Axis
- [[SIGGRAPH2009](http://www-evasion.imag.fr/people/Franck.Hetroy/Teaching/ProjetsImage/2010/Bib/tagliasacchi_zhang_cohen-or-siggraph2009.pdf)] Curve Skeleton Extraction from Incomplete Point Cloud [[matlab](https://github.com/ataiya/rosa)] :star:
- [[TOG](https://arxiv.org/pdf/1908.04520.pdf)] SDM-NET: deep generative network for structured deformable mesh
- [[TOG](https://dl.acm.org/doi/pdf/10.1145/2601097.2601161?download=true)] Robust and Accurate Skeletal Rigging from Mesh Sequences :fire:
- [[TOG](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.309.729&rep=rep1&type=pdf)] L1-medial skeleton of point cloud [[C++](https://github.com/HongqiangWei/L1-Skeleton)] :fire:
- [[EUROGRAPHICS2016](https://onlinelibrary.wiley.com/doi/epdf/10.1111/cgf.12865)] 3D Skeletons: A State-of-the-Art Report :fire:
- [[SGP2012](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.261.3158&rep=rep1&type=pdf)] Mean Curvature Skeletons [[C++](https://github.com/ataiya/starlab-mcfskel)] :fire:
- [[SMIC2010](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5521461)] Point Cloud Skeletons via Laplacian-Based Contraction [[Matlab](https://github.com/ataiya/cloudcontr)] :fire:
---
## Shape & Scene Completion
- [[ECCV2022](https://arxiv.org/abs/2207.11467)] CompNVS: Novel View Synthesis with Scene Completion
- [[ECCV2022](https://arxiv.org/abs/2207.11790)] PatchRD: Detail-Preserving Shape Completion by Learning Patch Retrieval and Deformation [[Project](https://github.com/GitBoSun/PatchRD)]
- [[Arxiv](https://arxiv.org/abs/2202.02669v1)] SRPCN: Structure Retrieval based Point Completion Network
- [[ICRA2022](https://arxiv.org/abs/2202.03084v1)] Temporal Point Cloud Completion with Pose Disturbance
- [[Arxiv](https://arxiv.org/abs/2201.01858v1)] Towards realistic symmetry-based completion of previously unseen point clouds [[github](https://github.com/softserveinc-rnd/symmetry-3d-completion)]
#### Before 2022
- [[AAAI2022](https://arxiv.org/abs/2112.12925v1)] Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspective
- [[AAAI2022](https://arxiv.org/abs/2112.05324v1)] Attention-based Transformation from Latent Features to Point Clouds
- [[Arxiv](https://arxiv.org/abs/2112.00726v1)] MonoScene: Monocular 3D Semantic Scene Completion [[Project](https://github.com/cv-rits/MonoScene)]
- [[Arxiv](https://arxiv.org/abs/2111.14798v1)] Semi-supervised Implicit Scene Completion from Sparse LiDAR [[github](https://github.com/OPEN-AIR-SUN/SISC)]
- [[NeurIPS2021](https://arxiv.org/abs/2111.12702v1)] Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion [[github](https://github.com/wutong16/Density_aware_Chamfer_Distance)]
- [[Arxiv](https://arxiv.org/abs/2111.12242v1)] PU-Transformer: Point Cloud Upsampling Transformer
- [[BMVC2021](https://arxiv.org/abs/2111.10701v1)] Self-Supervised Point Cloud Completion via Inpainting
- [[IROS2021](https://arxiv.org/abs/2112.01840v1)] Graph-Guided Deformation for Point Cloud Completion
- [[IROS2021](https://arxiv.org/abs/2109.11453v1)] Semantic Segmentation-assisted Scene Completion for LiDAR Point Clouds [[github](https://github.com/jokester-zzz/SSA-SC)]
- [[Arxiv](https://arxiv.org/abs/2109.10161v1)] 3D Point Cloud Completion with Geometric-Aware Adversarial Augmentation
- [[Arxiv](https://arxiv.org/abs/2109.09337v1)] PC2-PU: Patch Correlation and Position Correction for Effective Point Cloud Upsampling
- [[ICCV2021](https://arxiv.org/abs/2108.09936v1)] Voxel-based Network for Shape Completion by Leveraging Edge Generation [[github](https://github.com/xiaogangw/VE-PCN)]
- [[ICCV2021](https://arxiv.org/abs/2108.08839v1)] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers [[github](https://github.com/yuxumin/PoinTr)]
- [[ICCV2021](https://arxiv.org/abs/2108.04444v1)] SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer [[github](https://github.com/AllenXiangX/SnowflakeNet)]
- [[Arxiv](https://arxiv.org/abs/2107.13452v1)] CarveNet: Carving Point-Block for Complex 3D Shape Completion
- [[IJCAI2021](https://arxiv.org/abs/2106.15413v1)] IMENet: Joint 3D Semantic Scene Completion and 2D Semantic Segmentation through Iterative Mutual Enhancement
- [[CVPR2021](https://arxiv.org/abs/2106.04779v1)] Point Cloud Upsampling via Disentangled Refinement [[github](https://github.com/liruihui/Dis-PU)]
- [[TVCG2021](https://arxiv.org/abs/2106.00329)] Consistent Two-Flow Network for Tele-Registration of Point Clouds [[Project](https://vcc.tech/research/2021/CTFNet)]
- [[Arxiv](https://arxiv.org/abs/2105.01905)] 4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface [[Project](https://github.com/rabbityl/DeformingThings4D)]
- [[CVPR2021](https://arxiv.org/pdf/2104.13366.pdf)] Unsupervised 3D Shape Completion through GAN Inversion [[Project](https://junzhezhang.github.io/projects/ShapeInversion/)]
- [[Arxiv](https://arxiv.org/abs/2104.09587)] ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion
- [[CVPR2021](https://arxiv.org/pdf/2104.10154.pdf)] Variational Relational Point Completion Network [[Project](https://paul007pl.github.io/projects/VRCNet)]
- [[CVPR2021](https://arxiv.org/abs/2104.05666)] View-Guided Point Cloud Completion
- [[CVPR2021](https://arxiv.org/pdf/2104.03640v1.pdf)] Semantic Scene Completion via Integrating Instances and Scene in-the-Loop [[pytorch](https://github.com/yjcaimeow/SISNet)]
- [[CVPR2021](https://arxiv.org/pdf/2103.16671v1.pdf)] Denoise and Contrast for Category Agnostic Shape Completion
- [[CVPR2021](https://arxiv.org/pdf/2103.07838.pdf)] Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding
- [[CVPR2021](https://arxiv.org/abs/2012.03408v2)] PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Paths
- [[CVPR2021](https://arxiv.org/pdf/2103.02535.pdf)] Style-based Point Generator with Adversarial Rendering for Point Cloud Completion
- [[Arxiv](https://arxiv.org/pdf/2008.03404.pdf)] VPC-Net: Completion of 3D Vehicles from MLS Point Clouds
#### Before 2021
- [[Arxiv](https://arxiv.org/pdf/2012.03408.pdf)] PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Paths
- [[Arxiv](https://arxiv.org/pdf/2012.09242.pdf)] S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds
- [[Arxiv](https://arxiv.org/pdf/2011.09141.pdf)] Semantic Scene Completion using Local Deep Implicit Functions on LiDAR Data
- [[Arxiv](https://arxiv.org/pdf/2011.03981.pdf)] Learning-based 3D Occupancy Prediction for Autonomous Navigation in Occluded Environments
- [[Arxiv](https://arxiv.org/pdf/2012.03408.pdf)] PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Paths
- [[3DV2020](https://arxiv.org/pdf/2010.13662.pdf)] SCFusion: Real-time Incremental Scene Reconstruction
with Semantic Completion
- [[Arxiv](https://arxiv.org/pdf/2010.04278.pdf)] Refinement of Predicted Missing Parts Enhance Point Cloud
Completion [[pytorch](https://github.com/ivansipiran/Refinement-Point-Cloud-Completion)]
- [[Arxiv](https://arxiv.org/pdf/2009.05290.pdf)] Unsupervised Partial Point Set Registration via
Joint Shape Completion and Registration
- [[Arxiv](https://arxiv.org/abs/2008.10559)] LMSCNet: Lightweight Multiscale 3D Semantic Completion [[Demo](https://www.youtube.com/watch?v=XuEz0mbv2IQ&feature=youtu.be)]
- [[ECCV2020](https://arxiv.org/abs/2008.07358v1)] SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification
- [[ECCV2020](http://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123500273.pdf)] Weakly-supervised 3D Shape Completion in the Wild
- [[Arxiv](https://arxiv.org/pdf/2008.00394.pdf)] Point Cloud Completion by Learning Shape Priors
- [[Arxiv](https://arxiv.org/pdf/2008.00096.pdf)] KAPLAN: A 3D Point Descriptor for Shape Completion
- [[Arxiv](https://arxiv.org/pdf/2008.03404.pdf)] VPC-Net: Completion of 3D Vehicles from MLS Point Clouds
- [[Arxiv](https://arxiv.org/pdf/2006.14660.pdf)] SPSG: Self-Supervised Photometric Scene Generation from RGB-D Scans
- [[Arxiv](https://arxiv.org/pdf/2006.03761.pdf)] GRNet: Gridding Residual Network for Dense Point Cloud Completion
- [[Arxiv](https://arxiv.org/pdf/2006.03762.pdf)] Deep Octree-based CNNs with Output-Guided Skip Connections
for 3D Shape and Scene Completion
- [[CVPR2020](https://arxiv.org/pdf/2005.03871.pdf)] Point Cloud Completion by Skip-attention Network with Hierarchical Folding
- [[CVPR2020](https://arxiv.org/pdf/2004.03327.pdf)] Cascaded Refinement Network for Point Cloud Completion [[github](https://github.com/xiaogangw/cascaded-point-completion)]
- [[CVPR2020](https://arxiv.org/pdf/2004.02122.pdf)] Anisotropic Convolutional Networks for 3D Semantic Scene Completion [[github](https://github.com/waterljwant/SSC)]
- [[AAAI2020](https://arxiv.org/pdf/2003.13910.pdf)] Attention-based Multi-modal Fusion Network for Semantic Scene Completion
- [[CVPR2020](https://arxiv.org/pdf/2003.14052.pdf)] 3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior [[github](https://github.com/charlesCXK/3D-SketchAware-SSC)]
- [[ECCV2020](https://arxiv.org/pdf/2003.07717.pdf)] Multimodal Shape Completion via Conditional Generative Adversarial Networks [[pytorch](https://github.com/ChrisWu1997/Multimodal-Shape-Completion)]
- [[CVPR2020](https://arxiv.org/pdf/1904.12012.pdf)] RevealNet: Seeing Behind Objects in RGB-D Scans
- [[CVPR2020](https://arxiv.org/pdf/2003.01456.pdf)] Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion
- [[CVPR2020](https://arxiv.org/pdf/2003.00410.pdf)] PF-Net: Point Fractal Network for 3D Point Cloud Completion
- [[Arxiv](https://arxiv.org/pdf/2002.07269.pdf)] 3D Gated Recurrent Fusion for Semantic Scene Completion
- [[ICCVW2019](https://arxiv.org/abs/1901.00212)] EdgeConnect: Structure Guided Image Inpainting using Edge Prediction [[pytorch](https://github.com/knazeri/edge-connect)] :fire::star:
- [[ICRA2020](https://arxiv.org/pdf/2001.10709.pdf)] Depth Based Semantic Scene Completion with Position Importance Aware Loss
- [[CVPR2020](https://arxiv.org/pdf/1912.00036.pdf)] SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans
- [[Arxiv](https://arxiv.org/pdf/1911.10949.pdf)] PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes
- [[ICLR2020](https://arxiv.org/pdf/1904.00069.pdf)] Unpaired Point Cloud Completion on Real Scans using Adversarial Training [[tensorflow](https://github.com/xuelin-chen/pcl2pcl-gan-pub)]
- [[AAAI2020](http://cseweb.ucsd.edu/~mil070/projects/AAAI2020/paper.pdf)] Morphing and Sampling Network for Dense Point Cloud Completion [[pytorch](https://github.com/Colin97/MSN-Point-Cloud-Completion)]
- [[ICCVW2019](http://openaccess.thecvf.com/content_ICCVW_2019/papers/GMDL/Hu_Render4Completion_Synthesizing_Multi-View_Depth_Maps_for_3D_Shape_Completion_ICCVW_2019_paper.pdf)] Render4Completion: Synthesizing Multi-View Depth Maps for 3D Shape
Completion
- [[ICCV2019](http://openaccess.thecvf.com/content_ICCV_2019/papers/Wang_ForkNet_Multi-Branch_Volumetric_Semantic_Completion_From_a_Single_Depth_Image_ICCV_2019_paper.pdf)] ForkNet: Multi-branch Volumetric Semantic Completion
from a Single Depth Image [[tensorflow](https://github.com/wangyida/forknet)]
- [[ICCV2019](http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhang_Cascaded_Context_Pyramid_for_Full-Resolution_3D_Semantic_Scene_Completion_ICCV_2019_paper.pdf)] Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion [[Caffe3D](https://github.com/Pchank/CCPNet)]
- [[ICCV2019](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
- [[Arxiv](https://arxiv.org/pdf/1908.02893.pdf)] EdgeNet: Semantic Scene Completion from RGB-D images
- [[CVPR2019](http://openaccess.thecvf.com/content_CVPR_2019/papers/Tchapmi_TopNet_Structural_Point_Cloud_Decoder_CVPR_2019_paper.pdf)] TopNet: Structural Point Cloud Decoder [[pytorch & tensorflow](https://github.com/lynetcha/completion3d)]
- [[CVPR2019](http://openaccess.thecvf.com/content_CVPR_2019/papers/Han_Deep_Reinforcement_Learning_of_Volume-Guided_Progressive_View_Inpainting_for_3D_CVPR_2019_paper.pdf)] Deep Reinforcement Learning of Volume-guided Progressive View Inpainting for 3D Point Scene Completion from a Single Depth Image
- [[CVPR2019](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)]
- [[CVPR2019](http://openaccess.thecvf.com/content_CVPR_2019/papers/Sarmad_RL-GAN-Net_A_Reinforcement_Learning_Agent_Controlled_GAN_Network_for_Real-Time_CVPR_2019_paper.pdf)] RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion [[pytorch](https://github.com/iSarmad/RL-GAN-Net)]
- [[3DV2018](https://arxiv.org/pdf/1808.00671.pdf)] PCN: Point Completion Network [[tensorflow](https://github.com/wentaoyuan/pcn)] :fire:
- [[ECCV2018](http://openaccess.thecvf.com/content_ECCV_2018/papers/Jiahui_Zhang_Efficient_Semantic_Scene_ECCV_2018_paper.pdf)] Efficient Semantic Scene Completion Network with Spatial Group Convolution [[pytorch](https://github.com/zjhthu/SGC-Release)]
- [[CVPR2018](https://arxiv.org/pdf/1712.10215.pdf)] ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans [[tensorflow](https://github.com/angeladai/ScanComplete)] :fire::star:
- [[CVPR2018](http://www.cvlibs.net/publications/Stutz2018CVPR.pdf)] Learning 3D Shape Completion from Laser Scan Data with Weak Supervision [[torch](https://github.com/davidstutz/cvpr2018-shape-completion)][[torch](https://github.com/davidstutz/daml-shape-completion)]
- [[IJCV2018](https://arxiv.org/abs/1805.07290)] Learning 3D Shape Completion under Weak Supervision [[torch](https://github.com/davidstutz/aml-improved-shape-completion)][[torch](https://github.com/davidstutz/ijcv2018-improved-shape-completion)]
- [[ICCV2017](https://arxiv.org/pdf/1709.07599.pdf)] High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference :star:
- [[ICCV2017](https://arxiv.org/pdf/1612.00101.pdf)] Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis [[torch](https://github.com/angeladai/cnncomplete)] :fire::star:
- [[CVPR2017](http://openaccess.thecvf.com/content_cvpr_2017/papers/Song_Semantic_Scene_Completion_CVPR_2017_paper.pdf)] Semantic Scene Completion from a Single Depth Image [[caffe](https://github.com/shurans/sscnet)] :fire::star:
- [[CVPR2016](https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Firman_Structured_Prediction_of_CVPR_2016_paper.pdf)] Structured Prediction of Unobserved Voxels From a Single Depth Image [[resource](http://visual.cs.ucl.ac.uk/pubs/depthPrediction/)] :star:
---
## Shape Reconstruction & Generation
- [[Arxiv](https://arxiv.org/abs/2304.01900)] PODIA-3D: Domain Adaptation of 3D Generative Model Across Large Domain Gap Using Pose-Preserved Text-to-Image Diffusion [[Project](https://gwang-kim.github.io/podia_3d/)]
- [[Arxiv](https://arxiv.org/abs/2303.17905)] 3D-aware Image Generation using 2D Diffusion Models [[Project](https://jeffreyxiang.github.io/ivid/)]
- [[Arxiv](https://arxiv.org/abs/2303.17015)] HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion [[Project](https://ziyaerkoc.com/hyperdiffusion/)]
- [[Arxiv](https://arxiv.org/abs/2304.02827)] DITTO-NeRF: Diffusion-based Iterative Text To Omni-directional 3D Model [[Project](https://janeyeon.github.io/ditto-nerf/)]
- [[Arxiv](https://arxiv.org/abs/2303.14184)] Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior [[Project](https://make-it-3d.github.io/)]
- [[Arxiv](https://arxiv.org/abs/2302.10663)] RealFusion: 360° Reconstruction of Any Object from a Single Image [[Project](https://lukemelas.github.io/realfusion/)]
- [[Arxiv](https://arxiv.org/abs/2303.05371)] 3DGen: Triplane Latent Diffusion for Textured Mesh Generation
- [[Arxiv](https://arxiv.org/abs/2303.07937)] Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation [[Project](https://ku-cvlab.github.io/3DFuse/)]
- [[CVPR2023](https://arxiv.org/abs/2303.07938)] Controllable Mesh Generation Through Sparse Latent Point Diffusion Models [[Project](https://slide-3d.github.io/)]
- [[CVPR2023](https://arxiv.org/abs/2303.07653)] NEF: Neural Edge Fields for 3D Parametric Curve Reconstruction from Multi-view Images [[Project](https://yunfan1202.github.io/NEF/)]
- [[ICLR2023](https://arxiv.org/abs/2303.08133)] MeshDiffusion: Score-based Generative 3D Mesh Modeling [[Project](https://meshdiffusion.github.io/)]
- [[CVPR2023](https://arxiv.org/abs/2303.09554)] PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervision [[Project](https://ktertikas.github.io/part_nerf)]
- [[Arxiv](https://arxiv.org/abs/2303.12789)] Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions [[Project](https://instruct-nerf2nerf.github.io/)]
- [[CVPR2023](https://drive.google.com/file/d/1c4kpN0mOy2KfGmEQAbt-Ks77wBJ4F6GT/view)] SINE: Semantic-driven Image-based NeRF Editing with Prior-guided Editing Field [[Project](https://zju3dv.github.io/sine/)]
- [[Arxiv](https://arxiv.org/abs/2303.02375)] NeuDA: Neural Deformable Anchor for High-Fidelity Implicit Surface Reconstruction
- [[Arxiv](https://arxiv.org/abs/2303.02091)] Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement [[Project](https://me.kiui.moe/nerf2mesh/)]
- [[Arxiv](https://arxiv.org/abs/2303.01416)] 3D generation on ImageNet [[Project](https://snap-research.github.io/3dgp/)]
- [[Arxiv](https://arxiv.org/abs/2302.08510)] Text-driven Visual Synthesis with Latent Diffusion Prior [[Project](https://latent-diffusion-prior.github.io/)]
- [[Arxiv](https://arxiv.org/abs/2302.06833)] VQ3D: Learning a 3D-Aware Generative Model on ImageNet [[Project](https://kylesargent.github.io/vq3d)]
- [[Arxiv](https://arxiv.org/abs/2302.01721)] TEXTure: Text-Guided Texturing of 3D Shapes [[Project](https://texturepaper.github.io/TEXTurePaper/)]
- [[Arxiv](https://arxiv.org/abs/2301.09629)] LEGO-Net: Learning Regular Rearrangements of Objects in Rooms [[Project](https://ivl.cs.brown.edu/#/projects/lego-net)]
- [[Arxiv](https://arxiv.org/abs/2212.11984)] DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-aware Scene Synthesis [[Project](https://snap-research.github.io/discoscene/)]
- [[Arxiv](https://arxiv.org/abs/2212.11715)] GeoCode: Interpretable Shape Programs [[Project](https://threedle.github.io/GeoCode/)]
- [[Arxiv](https://arxiv.org/abs/2212.14704)] Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models [[Project](https://bluestyle97.github.io/dream3d/)]
- [[Arxiv](https://arxiv.org/abs/2212.08751)] Point-E: A System for Generating 3D Point Clouds from Complex Prompts [[Project](https://github.com/openai/point-e)]
- [[Arxiv](https://arxiv.org/abs/2212.04981)] LoopDraw: a Loop-Based Autoregressive Model for Shape Synthesis and Editing
- [[Arxiv](https://arxiv.org/abs/2212.04493)] SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation [[Project](https://yccyenchicheng.github.io/SDFusion/)]
- [[Arxiv](https://arxiv.org/abs/2212.03267)] NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors
- [[Arxiv](https://arxiv.org/abs/2212.03293)] Diffusion-SDF: Text-to-Shape via Voxelized Diffusion [[Project](https://github.com/ttlmh/Diffusion-SDF)]
- [[Arxiv](https://arxiv.org/abs/2212.00842)] 3D-LDM: Neural Implicit 3D Shape Generation with Latent Diffusion Models
- [[Arxiv](https://arxiv.org/abs/2212.00774)] Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation [[Project](https://pals.ttic.edu/p/score-jacobian-chaining)]
- [[Arxiv](https://arxiv.org/abs/2212.00792)] SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction [[Project](https://sparsefusion.github.io/)]
- [[Arxiv](https://arxiv.org/abs/2211.16677)] 3D Neural Field Generation using Triplane Diffusion [[Project](https://jryanshue.com/nfd/)]
- [[Arxiv](https://arxiv.org/abs/2210.03158)] Neural Volumetric Mesh Generator
- [[Arxiv](https://arxiv.org/abs/2211.13220)] Tetrahedral Diffusion Models for 3D Shape Generation
- [[Arxiv](https://arxiv.org/abs/2211.12497)] MagicPony: Learning Articulated 3D Animals in the Wild [[Project](https://3dmagicpony.github.io/)]
- [[Arxiv](https://arxiv.org/abs/2211.09869)] RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation [[Project](https://github.com/Anciukevicius/RenderDiffusion)]
- [[Arxiv](https://arxiv.org/abs/2211.10440)] Magic3D: High-Resolution Text-to-3D Content Creation [[Project](https://deepimagination.cc/Magic3D/)]
- [[Arxiv](https://arxiv.org/abs/2211.07600)] Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures
- [[NeurIPS2022](https://arxiv.org/abs/2210.06978)] LION: Latent Point Diffusion Models for 3D Shape Generation [[Project](https://nv-tlabs.github.io/LION/)]
- [[NeurIPS2022](https://nv-tlabs.github.io/GET3D/assets/paper.pdf)] GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images [[Project](https://nv-tlabs.github.io/GET3D/)]
- [[ECCV2022](https://arxiv.org/abs/2207.11795)] Cross-Modal 3D Shape Generation and Manipulation [[Project](https://people.cs.umass.edu/~zezhoucheng/edit3d/)]
- [[ECCV2022](https://arxiv.org/abs/2207.12298)] Deforming Radiance Fields with Cages
- [[NeurIPS2021](https://arxiv.org/abs/2110.07604)] NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild [[Project](https://jasonyzhang.com/ners/)]
- [[CVPR2022](https://arxiv.org/abs/2110.02624)] CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation [[github](https://github.com/AutodeskAILab/Clip-Forge)]
- [[CVPR2022](https://mworchel.github.io/assets/papers/neural_deferred_shading_with_supp.pdf)] Multi-View Mesh Reconstruction with Neural Deferred Shading [[Project](https://fraunhoferhhi.github.io/neural-deferred-shading/)]
- [[Arxiv](https://arxiv.org/abs/2206.15258)] Neural Surface Reconstruction of Dynamic Scenes with Monocular RGB-D Camera [[Project](https://ustc3dv.github.io/ndr/)]
- [[Arxiv](https://arxiv.org/abs/2206.08368)] Unbiased 4D: Monocular 4D Reconstruction with a Neural Deformation Model
- [[Arxiv](https://arxiv.org/abs/2205.13914)] 3DILG: Irregular Latent Grids for 3D Generative Modeling [[Project](https://1zb.github.io/3DILG/)]
- [[CVPR2022](https://arxiv.org/abs/2205.07763)] FvOR: Robust Joint Shape and Pose Optimization for Few-view Object Reconstruction [[Project](https://github.com/zhenpeiyang/FvOR/)]
- [[CVPR2022](https://arxiv.org/abs/2205.06267)] Topologically-Aware Deformation Fields for Single-View 3D Reconstruction [[Project](https://shivamduggal4.github.io/tars-3D/)]
- [[Arxiv](https://arxiv.org/abs/2204.10235)] Planes vs. Chairs: Category-guided 3D shape learning without any 3D cues [[Project](https://zixuanh.com/multiclass3D)]
- [[Arxiv](https://arxiv.org/abs/2204.06552)] Neural Vector Fields for Surface Representation and Inference
- [[CVPR2022](https://arxiv.org/abs/2204.03642)] Pre-train, Self-train, Distill: A simple recipe for Supersizing 3D Reconstruction [[Project](https://shubhtuls.github.io/ss3d/)]
- [[CVPR2022](https://arxiv.org/abs/2203.15536)] BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information [[Project](https://barc.is.tue.mpg.de/)]
- [[CVPR2022](https://arxiv.org/pdf/2203.11938.pdf)] φ-SfT: Shape-from-Template with a Physics-Based Deformation Model [[Project](https://4dqv.mpi-inf.mpg.de/phi-SfT/)]
- [[CVPR2022](https://arxiv.org/abs/2203.07977)] OcclusionFusion: Occlusion-aware Motion Estimation for Real-time Dynamic 3D Reconstruction [[Project](https://wenbin-lin.github.io/OcclusionFusion/)]
- [[Arxiv](https://arxiv.org/abs/2202.01999)] Neural Dual Contouring
- [[Arxiv](https://arxiv.org/abs/2201.01831v1)] POCO: Point Convolution for Surface Reconstruction [[Project](https://github.com/valeoai/POCO)]
- [[ICCV2021](https://arxiv.org/abs/2201.00112v1)] SurfGen: Adversarial 3D Shape Synthesis with Explicit Surface Discriminators [[github](https://github.com/aluo-x/NeuralRaycaster)]
#### Before 2022
- [[Arxiv](https://arxiv.org/abs/2112.03258v1)] DoodleFormer: Creative Sketch Drawing with Transformers
- [[NeurIPS2021](https://arxiv.org/abs/2112.02091v1)] Class-agnostic Reconstruction of Dynamic Objects from Videos [[Project](https://jason718.github.io/redo/)]
- [[Arxiv](https://arxiv.org/abs/2112.00584v1)] The Shape Part Slot Machine: Contact-based Reasoning for Generating 3D Shapes from Parts
- [[Arxiv](https://arxiv.org/abs/2111.14549v1)] MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks [[github](https://github.com/cvlab-epfl/MeshUDF)]
- [[Arxiv](https://arxiv.org/abs/2111.14600v1)] TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers [[github](https://github.com/MegviiRobot/TransMVSNet)]
- [[Arxiv](https://arxiv.org/abs/2111.12772v1)] JoinABLe: Learning Bottom-up Assembly of Parametric CAD Joints
- [[Arxiv](https://arxiv.org/abs/2111.11491v1)] Image Based Reconstruction of Liquids from 2D Surface Detections
- [[Arxiv](https://arxiv.org/abs/2201.06845)] TaylorImNet for Fast 3D Shape Reconstruction Based on Implicit Surface Function
- [[NeurIPS2021](https://arxiv.org/abs/2111.04276v1)] Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis [[Project](https://nv-tlabs.github.io/DMTet/)]
- [[ICML2021](https://arxiv.org/pdf/2011.13495.pdf)] Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces [[tensorflow](https://github.com/mabaorui/NeuralPull)]
- [[Arxiv](https://arxiv.org/abs/2112.11427)] StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation [[Project](https://stylesdf.github.io/)]
- [[3DV2021](https://arxiv.org/abs/2110.11599v1)] High Fidelity 3D Reconstructions with Limited Physical Views [[Project](https://sites.google.com/view/high-fidelity-3d-neural-prior)]
- [[3DV2021](https://arxiv.org/abs/2110.11256v1)] Multi-Category Mesh Reconstruction From Image Collections [[github](https://arxiv.org/pdf/2110.11256v1.pdf)]
- [[Arxiv](https://arxiv.org/abs/2110.10784v1)] Style Agnostic 3D Reconstruction via Adversarial Style Transfer [[https://github.com/Felix-Petersen/style-agnostic-3d-reconstruction]()]
- [[Arxiv](https://arxiv.org/abs/2112.12761)] BANMo: Building Animatable 3D Neural Models from Many Casual Videos [[Project](https://banmo-www.github.io/)]
- [[Arxiv](https://arxiv.org/abs/2110.06679v1)] EditVAE: Unsupervised Part-Aware Controllable 3D Point Cloud Shape Generation
- [[Arxiv](https://arxiv.org/abs/2110.05472v1)] Differentiable Stereopsis: Meshes from multiple views using differentiable rendering [[Project](https://shubham-goel.github.io/ds/)]
- [[ICCV2021](https://arxiv.org/abs/2110.03900v1)] Neural Strokes: Stylized Line Drawing of 3D Shapes
- [[ACMMM2021](https://arxiv.org/abs/2109.04153v1)] Single Image 3D Object Estimation with Primitive Graph Networks
- [[Arxiv](https://arxiv.org/abs/2111.12480)] Octree Transformer: Autoregressive 3D Shape Generation on Hierarchically Structured Sequences
- [[Arxiv](https://arxiv.org/abs/2110.06199)] ABO: Dataset and Benchmarks for Real-World 3D Object Understanding [[Project](https://amazon-berkeley-objects.s3.amazonaws.com/index.html)]
- [[ICCV2021](https://arxiv.org/abs/2109.00512)] Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction [[github](https://github.com/facebookresearch/co3d)]
- [[Arxiv](https://arxiv.org/abs/2109.11844)] Learnable Triangulation for Deep Learning-based 3D Reconstruction of Objects of Arbitrary Topology from Single RGB Images
- [[ICCV2021](https://arxiv.org/abs/2108.09964v1)] Learning Signed Distance Field for Multi-view Surface Reconstruction
- [[Arxiv](https://arxiv.org/abs/2108.08477v1)] Image2Lego: Customized LEGO Set Generation from Images
- [[ICCV2021](https://arxiv.org/abs/2108.03746v1)] Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projection Matching [[github](https://github.com/chenchao15/2D_projection_matching)]
- [[Arxiv](https://arxiv.org/abs/2108.02708v1)] Object Wake-up: 3-D Object Reconstruction, Animation, and in-situ Rendering from a Single Image
- [[Arxiv](https://arxiv.org/abs/2107.10844v1)] DOVE: Learning Deformable 3D Objects by Watching Videos [[Project](https://dove3d.github.io/)]
- [[Arxiv](https://arxiv.org/abs/2107.09584)] Active 3D Shape Reconstruction from Vision and Touch
- [[NeurIPS2020](https://proceedings.neurips.cc//paper/2020/file/a3842ed7b3d0fe3ac263bcabd2999790-Paper.pdf)] 3D Shape Reconstruction from Vision and Touch [[pytorch](https://github.com/facebookresearch/3D-Vision-and-Touch)]
- [[Arxiv](https://arxiv.org/pdf/2106.12102v1.pdf)] LegoFormer: Transformers for Block-by-Block Multi-view 3D Reconstruction
- [[Arxiv](https://arxiv.org/pdf/2106.08762v1.pdf)] Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects
- [[Arxiv](https://arxiv.org/abs/2106.06533v1)] View Generalization for Single Image Textured 3D Models [[Project](https://nv-adlr.github.io/view-generalization)]
- [[Arxiv](https://arxiv.org/pdf/2106.03452v1.pdf)] Shape As Points: A Differentiable Poisson Solver
- [[Arxiv](https://arxiv.org/pdf/2106.03087v1.pdf)] Neural Implicit 3D Shapes from Single Images with Spatial Patterns
- [[IJCAI2021](https://arxiv.org/pdf/2106.01553.pdf)] Spline Positional Encoding for Learning 3D Implicit Signed Distance Fields
- [[Arxiv](https://arxiv.org/pdf/2105.14548.pdf)] Z2P: Instant Rendering of Point Clouds
- [[CVPR2021](https://arxiv.org/abs/2105.11599)] Multi-view 3D Reconstruction of a Texture-less Smooth Surface of Unknown Generic Reflectance
- [[CVPR2021](https://arxiv.org/abs/2105.09396)] Birds of a Feather: Capturing Avian Shape Models from Images [[Project](https://yufu-wang.github.io/aves/)]
- [[Arxiv](https://arxiv.org/pdf/2105.09492.pdf)] DeepCAD: A Deep Generative Network for Computer-Aided Design Models
- [[Arxiv](https://arxiv.org/pdf/2105.08016.pdf)] StrobeNet: Category-Level Multiview Reconstruction of Articulated Objects
- [[CVPR2021](https://arxiv.org/pdf/2105.06663.pdf)] Sketch2Model: View-Aware 3D Modeling from Single Free-Hand Sketches
- [[Arxiv](https://arxiv.org/pdf/2105.03582.pdf)] Sign-Agnostic CONet: Learning Implicit Surface Reconstructions by Sign-Agnostic Optimization of Convolutional Occupancy Networks
- [[IJCAI2021](https://arxiv.org/pdf/2104.14769.pdf)] PointLIE: Locally Invertible Embedding for Point Cloud Sampling and Recovery
- [[Arxiv](https://arxiv.org/abs/2104.10078)] UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction
- [[CVPR2021](https://arxiv.org/pdf/2104.06397.pdf)] Shape and Material Capture at Home
- [[CVPR2021](https://arxiv.org/pdf/2104.05289.pdf)] StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Vision [[Project](https://hy1995.top/StereoPIFuProject/)]
- [[Arxiv](https://arxiv.org/pdf/2104.05652.pdf)] CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assembly
- [[CVPR2021](https://arxiv.org/pdf/2104.00858v1.pdf)] Fully Understanding Generic Objects:
Modeling, Segmentation, and Reconstruction [[Project](http://cvlab.cse.msu.edu/project-fully3dobject.html)]
- [[CVPR2021](https://arxiv.org/abs/2103.16832v1)] Online Learning of a Probabilistic and Adaptive Scene Representation
- [[CVPR2021](https://arxiv.org/abs/2104.00476)] Fostering Generalization in Single-view 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priors
- [[Arxiv](https://arxiv.org/abs/2104.00482)] Sketch2Mesh: Reconstructing and Editing 3D Shapes from Sketches
- [[CVPR2021](https://arxiv.org/abs/2103.12266)] Deep Implicit Moving Least-Squares Functions for 3D Reconstruction [[Project](https://github.com/Andy97/DeepMLS)]
- [[Arxiv](https://arxiv.org/pdf/2103.02766.pdf)] PC2WF: 3D WIREFRAME RECONSTRUCTION FROM RAW POINT CLOUDS
- [[CVPR2021](https://arxiv.org/pdf/2103.01458.pdf)] Diffusion Probabilistic Models for 3D Point Cloud Generation
[[Project](https://github.com/luost26/diffusion-point-cloud)]
- [[Arxiv](https://arxiv.org/abs/2102.08860)] ShaRF: Shape-conditioned Radiance Fields from a Single View [[Project](http://www.krematas.com/sharf/index.html)]
- [[Arxiv](https://arxiv.org/pdf/2102.06195.pdf)] Shelf-Supervised Mesh Prediction in the Wild
- [[Arxiv](https://arxiv.org/pdf/2102.05973.pdf)] HyperPocket: Generative Point Cloud Completion
- [[Arxiv](https://arxiv.org/pdf/2102.02798.pdf)] Im2Vec: Synthesizing Vector Graphics without Vector Supervision [[resource](http://geometry.cs.ucl.ac.uk/projects/2020/Im2Vec/)]
- [[Arxiv](https://arxiv.org/pdf/2101.06860.pdf)] Secrets of 3D Implicit Object Shape Reconstruction in the Wild
- [[Arxiv](https://arxiv.org/pdf/2101.07889.pdf)] Joint Learning of 3D Shape Retrieval and Deformation
- [[Arxiv](https://arxiv.org/abs/2101.10994)] Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes
#### Before 2021
- [[Arxiv](https://arxiv.org/pdf/2012.01203.pdf)] Learning Delaunay Surface Elements for Mesh Reconstruction
- [[Arxiv](https://arxiv.org/pdf/2012.02493.pdf)] Compositionally Generalizable 3D Structure Prediction
- [[Arxiv](https://arxiv.org/pdf/2012.03196.pdf)] Online Adaptation for Consistent Mesh Reconstruction in the Wild
- [[Arxiv](https://arxiv.org/pdf/2012.07498.pdf)] Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction from Raw Point Clouds
- [[Arxiv](https://arxiv.org/pdf/2012.07241.pdf)] Deep Optimized Priors for 3D Shape Modeling and Reconstruction
- [[Arxiv](https://arxiv.org/pdf/2011.00844.pdf)] DO 2D GANS KNOW 3D SHAPE? UNSUPERVISED 3D SHAPE RECONSTRUCTION FROM 2D IMAGE GANS [[Project](https://xingangpan.github.io/projects/GAN2Shape.html)]
- [[Arxiv](https://arxiv.org/pdf/2011.02570.pdf)] DUDE: Deep Unsigned Distance Embeddings for Hi-Fidelity Representation of Complex 3D Surfaces
- [[3DV2020](https://arxiv.org/pdf/2011.04755.pdf)] Learning to Infer Semantic Parameters for 3D Shape Editing [[Project](https://github.com/weify627/learn-sem-param)]
- [[3DV2020](https://arxiv.org/pdf/2011.08026.pdf)] Cycle-Consistent Generative Rendering for 2D-3D Modality Translation [[Project](https://ttaa9.github.io/genren/)]
- [[3DV2020](https://arxiv.org/pdf/2011.08534.pdf)] A Divide et Impera Approach for 3D Shape Reconstruction from Multiple Views
- [[Arxiv](https://arxiv.org/pdf/2011.11567.pdf)] A Closed-Form Solution to Local Non-Rigid Structure-from-Motion
- [[Arxiv](https://arxiv.org/pdf/2011.13650.pdf)] Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondence
- [[Arxiv](https://arxiv.org/pdf/2011.13961.pdf)] D-NeRF: Neural Radiance Fields for Dynamic Scenes
- [[Arxiv](https://arxiv.org/pdf/2011.03277.pdf)] Modular Primitives for High-Performance Differentiable Rendering
- [[CVPR2021](https://arxiv.org/pdf/2011.14791.pdf)] NeuralFusion: Online Depth Fusion in Latent Space
- [[Arxiv](https://arxiv.org/abs/2012.12247)] Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Deforming Scene from Monocular Video [[Project](https://gvv.mpi-inf.mpg.de/projects/nonrigid_nerf/)]
- [[NeurIPS2020](https://arxiv.org/abs/2007.15627)] Continuous Object Representation Networks: Novel View Synthesis without Target View Supervision [[Project](https://nicolaihaeni.github.io/corn/)]
- [[NeurIPS2020](https://proceedings.neurips.cc/paper/2020/file/83fa5a432ae55c253d0e60dbfa716723-Paper.pdf)] SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images [[Project](https://chenhsuanlin.bitbucket.io/signed-distance-SRN/)]
- [[NeurIPS2020](https://proceedings.neurips.cc/paper/2020/file/1a77befc3b608d6ed363567685f70e1e-Paper.pdf)] Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance [[Project](https://lioryariv.github.io/idr/)]
- [[NeurIPS2020](https://proceedings.neurips.cc/paper/2020/file/098d86c982354a96556bd861823ebfbd-Paper.pdf)] Convolutional Generation of Textured 3D Meshes [[Project](https://github.com/dariopavllo/convmesh)]
- [[Arxiv](https://arxiv.org/pdf/2012.04641.pdf)] Vid2CAD: CAD Model Alignment using Multi-View Constraints from Videos
- [[NeurIPS2020](https://proceedings.neurips.cc/paper/2020/file/21327ba33b3689e713cdff1641128004-Paper.pdf)] UCLID-Net: Single View Reconstruction in Objec Space [[Project](https://github.com/cvlab-epfl/UCLID-Net)]
- [[NeurIPS2020](https://arxiv.org/abs/2008.02792)] CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations
[[Project](https://geometry.stanford.edu/projects/caspr/)]
- [[NeurIPS2020](https://proceedings.neurips.cc/paper/2020/file/45fbc6d3e05ebd93369ce542e8f2322d-Paper.pdf)] Generative 3D Part Assembly via Dynamic Graph Learning [[pytorch](https://github.com/hyperplane-lab/Generative-3D-Part-Assembly)]
- [[NeurIPS2020](https://proceedings.neurips.cc/paper/2020/file/7137debd45ae4d0ab9aa953017286b20-Paper.pdf)] Learning Deformable Tetrahedral Meshes for 3D Reconstruction [[Project](https://nv-tlabs.github.io/DefTet/)]
- [[NeurIPS2020](https://proceedings.neurips.cc/paper/2020/file/bdbca288fee7f92f2bfa9f7012727740-Paper.pdf)] SoftFlow: Probabilistic Framework for Normalizing Flow on Manifolds [[pytorch](https://github.com/ANLGBOY/SoftFlow)]
- [[Arxiv](https://arxiv.org/pdf/2010.08276.pdf)] Training Data Generating Networks: Linking 3D Shapes and Few-Shot Classification
- [[Arxiv](https://arxiv.org/pdf/2010.08682.pdf)] MESHMVS: MULTI-VIEW STEREO GUIDED MESH RECONSTRUCTION
- [[Arxiv](https://arxiv.org/pdf/2010.11378.pdf)] Learning Occupancy Function from Point Clouds for Surface Reconstruction
- [[NeurIPS2020](https://arxiv.org/pdf/2010.10505.pdf)] SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images [[Project](https://chenhsuanlin.bitbucket.io/signed-distance-SRN/)]
- [[Arxiv](https://arxiv.org/abs/2010.04595)] GRF: Learning a General Radiance Field for 3D Scene Representation and Rendering [[github](https://github.com/alextrevithick/GRF)]
- [[3DV2020](https://arxiv.org/pdf/2010.05391.pdf)] A Progressive Conditional Generative Adversarial Network
for Generating Dense and Colored 3D Point Clouds
- [[3DV2020](https://arxiv.org/pdf/2010.07021.pdf)] Better Patch Stitching for Parametric Surface Reconstruction
- [[NeurIPS2020](https://arxiv.org/pdf/2010.07428.pdf)] Skeleton-bridged Point Completion: From Global
Inference to Local Adjustment [[Project Page](https://yinyunie.github.io/SKPCN-page/)]
- [[Arxiv](https://arxiv.org/abs/2010.07492)] NeRF++: Analyzing and Improving Neural Radiance Fields [[pytorch](https://github.com/Kai-46/nerfplusplus)]
- [[Arxiv](https://arxiv.org/pdf/2009.03298.pdf)] Improved Modeling of 3D Shapes with Multi-view Depth Maps
- [[SIGGRAPH2020](https://arxiv.org/abs/2008.12298)] One Shot 3D Photography [[Project](https://facebookresearch.github.io/one_shot_3d_photography/)]
- [[BMVC2020](https://arxiv.org/pdf/2008.11762.pdf)] Large Scale Photometric Bundle Adjustment
- [[ECCV2020](https://arxiv.org/abs/2008.10719)] Interactive Annotation of 3D Object Geometry using 2D Scribbles [[Project](http://www.cs.toronto.edu/~shenti11/scribble3d/)]
- [[BMVC2020](https://arxiv.org/abs/2008.07928)] Visibility-aware Multi-view Stereo Network
- [[ECCV2020](https://arxiv.org/abs/2008.07760)] Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images
- [[ECCV2020](https://arxiv.org/abs/2008.06133)] 3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View [[Project](https://marcbadger.github.io/avian-mesh/)][[Pytorch](https://github.com/marcbadger/avian-mesh)]
- [[BMVC2020](https://arxiv.org/abs/1912.04663)] 3D-GMNet: Single-View 3D Shape Recovery as A Gaussian Mixture
- [[SIGGRAPH2020](https://arxiv.org/pdf/2008.06471.pdf)] Self-Sampling for Neural Point Cloud Consolidation
- [[ECCV2020](https://arxiv.org/abs/2008.00446)] Stochastic Bundle Adjustment for Efficient and Scalable 3D Reconstruction [[github](https://github.com/zlthinker/STBA)]
- [[Arxiv](https://arxiv.org/abs/2008.02268)] NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections [[Project](https://nerf-w.github.io/)]
- [[Arxiv](https://arxiv.org/pdf/2005.11617.pdf)] MeshODE: A Robust and Scalable Framework for Mesh Deformation
- [[Arxiv](https://arxiv.org/pdf/2007.12944.pdf)] MRGAN: Multi-Rooted 3D Shape Generation with Unsupervised Part Disentanglement
- [[ECCV2020](https://arxiv.org/pdf/2007.09267.pdf)] Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance [[pytorch](https://github.com/Colin97/Point2Mesh)]
- [[ECCV2020](https://arxiv.org/pdf/2007.11110.pdf)] Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop
- [[ECCV2020](https://arxiv.org/pdf/2007.10872.pdf)] Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking
- [[ECCV2020](https://arxiv.org/pdf/2007.10982.pdf)] Shape and Viewpoint without Keypoints
- [[Arxiv](https://arxiv.org/pdf/2007.10300.pdf)] Object-Centric Multi-View Aggregation
- [[ECCV2020](https://arxiv.org/pdf/2007.10453.pdf)] Points2Surf Learning Implicit Surfaces from Point Clouds
- [[NeurIPS2020](https://arxiv.org/pdf/2007.10973.pdf)] Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows [[Project](https://kunalmgupta.github.io/projects/NeuralMeshflow.html)]
- [[Arxiv](https://arxiv.org/pdf/2006.12250.pdf)] Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images
- [[Arxiv](https://arxiv.org/pdf/2006.13240.pdf)] Neural Non-Rigid Tracking
- [[NeurIPS2020](https://arxiv.org/pdf/2006.03997.pdf)] MeshSDF: Differentiable Iso-Surface Extraction
- [[Arxiv](https://arxiv.org/pdf/2006.07752.pdf)] 3D Reconstruction of Novel Object Shapes from Single Images
- [[NeurIPS2020](https://arxiv.org/pdf/2006.07982.pdf)] ShapeFlow: Learnable Deformations Among 3D Shapes [[pytorch](https://github.com/maxjiang93/ShapeFlow)]
- [[Arxiv](https://arxiv.org/pdf/2006.09694.pdf)] 3D Shape Reconstruction from Free-Hand Sketches
- [[Arxiv](https://arxiv.org/pdf/2003.04618.pdf)] Convolutional Occupancy Networks
- [[Siggraph2020](https://arxiv.org/pdf/2005.11084.pdf)] Point2Mesh: A Self-Prior for Deformable Meshes
- [[Arxiv](https://arxiv.org/pdf/2005.02138.pdf)] PointTriNet: Learned Triangulation of 3D Point
- [[Arxiv](https://arxiv.org/pdf/2005.04623.pdf)] A Simple and Scalable Shape Representation for 3D Reconstruction
- [[Siggraph2020](https://arxiv.org/pdf/2005.03372.pdf)] Vid2Curve: Simultaneously Camera Motion Estimation and Thin Structure Reconstruction from an RGB Video
- [[CVPR2020](https://arxiv.org/pdf/2005.01939.pdf)] From Image Collections to Point Clouds with Self-supervised Shape and Pose Networks [[tensorflow](https://github.com/val-iisc/ssl_3d_recon)]
- [[CVPR2020](https://arxiv.org/pdf/2004.10904.pdf)] Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes [[github](https://github.com/lzqsd/TransparentShapeReconstruction)]
- [[Arxiv](https://arxiv.org/pdf/2002.10880.pdf)] PolyGen: An Autoregressive Generative Model of 3D Meshes
- [[Arxiv](https://arxiv.org/pdf/2004.07414.pdf)] Combinatorial 3D Shape Generation via Sequential Assembly
- [[Arxiv](https://arxiv.org/pdf/2004.06302.pdf)] Few-Shot Single-View 3-D Object Reconstruction with Compositional Priors
- [[Arxiv](https://arxiv.org/pdf/2004.04485.pdf)] Neural Object Descriptors for Multi-View Shape Reconstruction
- [[CVPR2020](https://arxiv.org/pdf/2003.14034.pdf)] SPARE3D: A Dataset for SPAtial REasoning on Three-View Line Drawings [[pytorch](https://github.com/ai4ce/SPARE3D)]
- [[Arxiv](https://arxiv.org/pdf/2003.12397.pdf)] Modeling 3D Shapes by Reinforcement Learning
- [[ECCV2020](https://arxiv.org/pdf/2003.12181.pdf)] ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds [[pytorch](https://github.com/Hippogriff/parsenet-codebase)]
- [[Arxiv](https://arxiv.org/pdf/2003.10016.pdf)] Self-Supervised 2D Image to 3D Shape Translation with Disentangled Representations
- [[Arxiv](https://arxiv.org/pdf/2003.09852.pdf)] Universal Differentiable Renderer for Implicit Neural Representations
- [[Arxiv](https://arxiv.org/pdf/2003.09754.pdf)] Learning 3D Part Assembly from a Single Image
- [[Arxiv](https://arxiv.org/pdf/2003.08593.pdf)] Curriculum DeepSDF
- [[Arxiv](https://arxiv.org/pdf/2003.08624.pdf)] PT2PC: Learning to Generate 3D Point Cloud Shapes from Part Tree Conditions
- [[Arxiv](https://arxiv.org/pdf/2003.06473.pdf)] Self-supervised Single-view 3D Reconstruction via Semantic Consistency
- [[Arxiv](https://arxiv.org/pdf/2003.03711.pdf)] Meta3D: Single-View 3D Object Reconstruction from Shape Priors in Memory
- [[Arxiv](https://arxiv.org/pdf/2003.03551.pdf)] STD-Net: Structure-preserving and Topology-adaptive Deformation Network for 3D Reconstruction from a Single Image [[new](https://arxiv.org/abs/2108.06682v1)]
- [[Arxiv](https://arxiv.org/pdf/2001.07884.pdf)] Curvature Regularized Surface Reconstruction from Point Cloud
- [[Arxiv](https://arxiv.org/pdf/2003.00802.pdf)] Hypernetwork approach to generating point clouds
- [[Arxiv](https://arxiv.org/pdf/2002.12674.pdf)] Inverse Graphics GAN: Learning to Generate 3D Shapes from Unstructured 2D Data
- [[Arxiv](https://arxiv.org/pdf/2001.01744.pdf)] Meshlet Priors for 3D Mesh Reconstruction
- [[Arxiv](https://arxiv.org/pdf/1912.10589.pdf)] Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction
- [[Arxiv](https://arxiv.org/pdf/1912.07109.pdf)] SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization
- [[CVPR2019](https://arxiv.org/pdf/1812.03828.pdf)] Occupancy Networks: Learning 3D Reconstruction in Function Space [[pytorch](https://github.com/autonomousvision/occupancy_networks)] :fire::star:
- [[NeurIPS2019](https://arxiv.org/pdf/1905.10711.pdf)] DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction [[tensorflow](https://github.com/laughtervv/DISN)]
- [[NeurIPS2019](https://arxiv.org/pdf/1905.10711.pdf)] Learning to Infer Implicit Surfaces without 3D Supervision
- [[CVPR2019](http://openaccess.thecvf.com/content_CVPR_2019/papers/Tang_A_Skeleton-Bridged_Deep_Learning_Approach_for_Generating_Meshes_of_Complex_CVPR_2019_paper.pdf)] A Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Images [[pytorch & tensorflow](https://github.com/tangjiapeng/SkeletonBridgeRecon)]
- [[Arxiv](https://arxiv.org/pdf/1901.06802.pdf)] Deep Level Sets: Implicit Surface Representations for 3D Shape Inference
- [[CVPR2019](https://arxiv.org/pdf/1812.02822.pdf)] Learning Implicit Fields for Generative Shape Modeling [[tensorflow](https://github.com/czq142857/implicit-decoder)] :fire:
- [[ICCV2019](http://openaccess.thecvf.com/content_ICCV_2019/papers/Chen_Point-Based_Multi-View_Stereo_Network_ICCV_2019_paper.pdf)] Point-based Multi-view Stereo Network [[pytorch](https://github.com/callmeray/PointMVSNet)] :star:
- [[Arxiv](https://arxiv.org/pdf/1911.07401.pdf)] TSRNet: Scalable 3D Surface Reconstruction Network for Point Clouds using Tangent Convolution
- [[Arxiv](https://arxiv.org/ftp/arxiv/papers/1911/1911.09204.pdf)] DR-KFD: A Differentiable Visual Metric for 3D Shape Reconstruction
- [[ICCV2019](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
- [[ICCV2019](http://openaccess.thecvf.com/content_ICCV_2019/papers/Wen_Pixel2Mesh_Multi-View_3D_Mesh_Generation_via_Deformation_ICCV_2019_paper.pdf)] Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation [[pytorch](https://github.com/walsvid/Pixel2MeshPlusPlus)]
- [[ICCV2019](http://openaccess.thecvf.com/content_ICCV_2019/papers/Wallace_Few-Shot_Generalization_for_Single-Image_3D_Reconstruction_via_Priors_ICCV_2019_paper.pdf)] Few-Shot Generalization for Single-Image 3D Reconstruction via Priors
- [[ICCV2019](https://arxiv.org/pdf/1909.00321.pdf)] Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networks
- [[AAAI2018](https://arxiv.org/pdf/1706.07036.pdf)] Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction [[tensorflow](https://github.com/chenhsuanlin/3D-point-cloud-generation)] :star::fire:
- [[NeurIPS2017](https://papers.nips.cc/paper/6657-marrnet-3d-shape-reconstruction-via-25d-sketches.pdf)] MarrNet: 3D Shape Reconstruction via 2.5D Sketches [[torch](https://github.com/jiajunwu/marrnet)]:star::fire:
---
## 3D Scene Understanding
- [[Arxiv](https://arxiv.org/abs/2303.04748)] CLIP-FO3D: Learning Free Open-world 3D Scene Representations from 2D Dense CLIP
- [[CVPR2023](https://arxiv.org/abs/2211.14157)] Learning 3D Scene Priors with 2D Supervision [[Project](https://yinyunie.github.io/sceneprior-page/)]
- [[CVPR2023](https://arxiv.org/abs/2302.14746)] Mask3D: Pre-training 2D Vision Transformers by Learning Masked 3D Priors
- [[Arxiv](https://arxiv.org/abs/2302.12827)] Decoupling Human and Camera Motion from Videos in the Wild [[Project](https://vye16.github.io/slahmr/)]
- [[CVPR2022](https://openaccess.thecvf.com/content/CVPR2022/papers/Yeh_PhotoScene_Photorealistic_Material_and_Lighting_Transfer_for_Indoor_Scenes_CVPR_2022_paper.pdf)] PhotoScene: Photorealistic Material and Lighting Transfer for Indoor Scenes [[github](https://github.com/ViLab-UCSD/photoscene)]
- [[Arxiv](https://arxiv.org/abs/2206.01203)] Semantic Instance Segmentation of 3D Scenes Through Weak Bounding Box Supervision [[Project](http://virtualhumans.mpi-inf.mpg.de/box2mask/)]
- [[CVPR2022](https://arxiv.org/abs/2204.07548)] Learning Multi-View Aggregation In the Wild for Large-Scale 3D Semantic Segmentation [[github](https://github.com/drprojects/DeepViewAgg)]
- [[CVPR2022](https://arxiv.org/abs/2204.06272)] 3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection
- [[CVPR2022](https://arxiv.org/abs/2204.06950)] BEHAVE: Dataset and Method for Tracking Human Object Interactions [[Project](http://virtualhumans.mpi-inf.mpg.de/behave/)]
#### Before 2022
- [[Arxiv](https://arxiv.org/abs/2112.11340v1)] Transferable End-to-end Room Layout Estimation via Implicit Encoding [[Project](https://sites.google.com/view/transferrl/)]
- [[Arxiv](https://arxiv.org/abs/2112.10482v1)] ScanQA: 3D Question Answering for Spatial Scene Understanding
- [[Arxiv](https://arxiv.org/abs/2112.08359v1)] 3D Question Answering
- [[Arxiv](https://arxiv.org/abs/2112.06133v1)] MVLayoutNet:3D layout reconstruction with multi-view panoramas
- [[SGP2021](https://arxiv.org/abs/2112.05644v1)] Roominoes: Generating Novel 3D Floor Plans From Existing 3D Rooms
- [[Arxiv](https://arxiv.org/abs/2112.02990v1)] 4DContrast: Contrastive Learning with Dynamic Correspondences for 3D Scene Understanding
- [[Arxiv](https://arxiv.org/abs/2112.03030v1)] Pose2Room: Understanding 3D Scenes from Human Activities [[Project](https://yinyunie.github.io/pose2room-page/)]
- [[NeurIPS2021](https://arxiv.org/abs/2112.01001v1)] SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency [[Project](https://devendrachaplot.github.io/projects/seal)]
- [[Arxiv](https://arxiv.org/abs/2112.01551v1)] D3Net: A Speaker-Listener Architecture for Semi-supervised Dense Captioning and Visual Grounding in RGB-D Scans [[Project](https://daveredrum.github.io/D3Net/)]
- [[Arxiv](https://arxiv.org/abs/2112.01520v1)] Recognizing Scenes from Novel Viewpoints
- [[Arxiv](https://arxiv.org/abs/2112.01316v1)] Putting 3D Spatially Sparse Networks on a Diet
- [[Arxiv](https://arxiv.org/abs/2111.12608v1)] Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing [[github](https://github.com/OPEN-AIR-SUN/Cerberus)]
- [[NeurIPS2021](https://arxiv.org/abs/2111.01253v1)] Neural Scene Flow Prior [[github](https://github.com/Lilac-Lee/Neural_Scene_Flow_Prior)]
- [[ICCV2021](https://arxiv.org/abs/2110.01997v1)] Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Images [[Project](https://github.com/ybarancan/STSU)]
- [[Arxiv](https://arxiv.org/abs/2110.00644v1)] RoomStructNet: Learning to Rank Non-Cuboidal Room Layouts From Single View
- [[EMNLP2021](https://arxiv.org/abs/2109.15207v1)] Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments [[Project](https://3dlg-hcvc.github.io/LAW-VLNCE/)]
- [[Arxiv](https://arxiv.org/abs/2109.13410v1)] KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D [[Project](http://www.cvlibs.net/datasets/kitti-360/)]
- [[CVPR2021](https://arxiv.org/abs/2007.12868)] OpenRooms: An End-to-End Open Framework for Pho