A list of papers, libraries and datasets I recently read is collected for anyone who shows interest at

• 3D Detection & Segmentation
• Shape Representation
• Shape & Scene Completion
• Shape Reconstruction
• 3D Scene Understanding
• 3D Scene Reconstruction
• NeRF
• About Human Body
• General Methods
• Others (inc. Networks in Classification, Matching, Registration, Alignment, Depth, Normal, Pose, Keypoints, etc.)
• Survey, Resources and Tools

Statistics: 🔥 code is available & stars >= 100  |  ⭐ citation >= 50

• [Arxiv] ImVoxelNet: Image to Voxels Projection for Monocular and Multi-View General-Purpose 3D Object Detection [Project]
• [CVPR2021] 3D Spatial Recognition without Spatially Labeled 3D [Project]
• [Arxiv] Lite-FPN for Keypoint-based Monocular 3D Object Detection
• [TPAMI] MonoGRNet: A General Framework for Monocular 3D Object Detection
• [Arxiv] Lidar Point Cloud Guided Monocular 3D Object Detection
• [Arxiv] Geometry-aware data augmentation for monocular 3D object detection
• [Arxiv] OCM3D: Object-Centric Monocular 3D Object Detection
• [CVPR2021] Objects are Different: Flexible Monocular 3D Object Detection [github]
• [CVPR2021] HVPR: Hybrid Voxel-Point Representation for Single-stage 3D Object Detection
• [Arxiv] Group-Free 3D Object Detection via Transformers [pytorch]
• [CVPR2021] GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection [pytorch]
• [CVPR2021] Back-tracing Representative Points for Voting-based 3D Object Detection in Point Clouds [pytorch]
• [CVPR2021] Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection [github]
• [CVPR2021] Delving into Localization Errors for Monocular 3D Object Detection [github]
• [Arxiv] 3D-MAN: 3D Multi-frame Attention Network for Object Detection
• [CVPR2021] LiDAR R-CNN: An Efficient and Universal 3D Object Detector [github]
• [CVPR2021] 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection [pytorch]
• [CVPR2021] M3DSSD: Monocular 3D Single Stage Object Detector
• [CVPR2021] MonoRUn: Monocular 3D Object Detection by Reconstruction and Uncertainty Propagation
• [Arxiv] SparsePoint: Fully End-to-End Sparse 3D Object Detector
• [Arxiv] RangeDet:In Defense of Range View for LiDAR-based 3D Object Detection
• [ICRA2021] YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection [github]
• [CVPR2021] ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection [github]
• [Arxiv] Offboard 3D Object Detection from Point Cloud Sequences
• [CVPR2021] DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution [github]
• [Arxiv] Pseudo-labeling for Scalable 3D Object Detection
• [Arxiv] DPointNet: A Density-Oriented PointNet for 3D Object Detection in Point Clouds
• [Arxiv] PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection [pytorch]
• [Arxiv] Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
• [Arxiv] CubifAE-3D: Monocular Camera Space Cubification for Auto-Encoder based 3D Object Detection
• [Arxiv] Self-Attention Based Context-Aware 3D Object Detection [pytorch]
• [Arxiv] Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection

• [Arxiv] It’s All Around You: Range-Guided Cylindrical Network for 3D Object Detection
• [Arxiv] 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection [Project]
• [Arxiv] Demystifying Pseudo-LiDAR for Monocular 3D Object Detection
• [3DV2020] PanoNet3D: Combining Semantic and Geometric Understanding for LiDAR Point Cloud Detection
• [AAAI2021] PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object Detection
• [Arxiv] SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation
• [Arxiv] 3D Object Detection with Pointformer
• [WACV2021] CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection [pytorch]
• [Arxiv] Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation [pytorch]
• [Arxiv] Learning to Predict the 3D Layout of a Scene
• [Arxiv] Canonical Voting: Towards Robust Oriented Bounding Box Detection in 3D Scenes [Project]
• [Arxiv] DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution
• [Arxiv] Temporal-Channel Transformer for 3D Lidar-Based Video Object Detection in Autonomous Driving
• [NeurIPS2020] Every View Counts: Cross-View Consistency in 3D Object Detection with Hybrid-Cylindrical-Spherical Voxelization
• [NeurIPS2020] Group Contextual Encoding for 3D Point Clouds [pytorch]
• [Arxiv] 3D Object Recognition By Corresponding and Quantizing Neural 3D Scene Representations [Project]
• [Arxiv] A Density-Aware PointRCNN for 3D Objection Detection in Point Clouds
• [Arxiv] Monocular 3D Detection with Geometric Constraints Embedding and Semi-supervised Training
• [ECCV2020] Reinforced Axial Refinement Network for Monocular 3D Object Detection
• [Arxiv] RUHSNet: 3D Object Detection Using Lidar Data in Real Time [pytorch]
• [IROS2020] 3D Multi-Object Tracking: A Baseline and New Evaluation Metrics [Project][Code]
• [ECCV2020] Virtual Multi-view Fusion for 3D Semantic Segmentation
• [ACMMM2020] Weakly Supervised 3D Object Detection from Point Clouds
• [ECCV2020] Weakly Supervised 3D Object Detection from Lidar Point Cloud [pytorch]
• [ECCV2020] Kinematic 3D Object Detection in Monocular Video
• [IROS2020] Object-Aware Centroid Voting for Monocular 3D Object Detection
• [ECCV2020] Pillar-based Object Detection for Autonomous Driving
• [Arxiv] Local Grid Rendering Networks for 3D Object Detection in Point Clouds
• [Arxiv] Learning to Detect 3D Objects from Point Clouds in Real Time
• [Arxiv] SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds
• [CVPR2020] PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
• [CVPR2020] FroDO: From Detections to 3D Objects
• [CVPR2020] Physically Realizable Adversarial Examples for LiDAR Object Detection
• [CVPR2020] Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection
• [CVPR2020] End-to-end 3D Point Cloud Instance Segmentation without Detection
• [CVPR2020] MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships
• [CVPR2020] Structure Aware Single-stage 3D Object Detection from Point Cloud
• [CVPR2020] Learning Depth-Guided Convolutions for Monocular 3D Object Detection [pytorch] 🔥
• [CVPR2020] What You See is What You Get: Exploiting Visibility for 3D Object Detection
• [CVPR2020] Density Based Clustering for 3D Object Detection in Point Clouds
• [CVPR2020] Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation
• [CVPR2020] End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection
• [CVPR2020] PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
• [CVPR2020] MLCVNet: Multi-Level Context VoteNet for 3D Object Detection
• [CVPR2020] PointPainting: Sequential Fusion for 3D Object Detection
• [CVPR2020] Joint 3D Instance Segmentation and Object Detection for Autonomous Driving
• [CVPR2020] Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud [tensorflow]
• [CVPR2020] Joint 3D Instance Segmentation and Object Detection for Autonomous Driving
• [CVPR2020] HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection
• [CVPR2020] A Hierarchical Graph Network for 3D Object Detection on Point Clouds
• [Arxiv] H3DNet: 3D Object Detection Using Hybrid Geometric Primitives
• [CVPR2020] P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds
• [Arxiv] 3D-CVF: Generating Joint Camera and LiDAR Features Using Cross-View Spatial Feature Fusion for 3D Object Detection
• [CVPR2020] Joint Spatial-Temporal Optimization for Stereo 3D Object Tracking
• [CVPR2020] Learning to Evaluate Perception Models Using Planner-Centric Metrics
• [CVPR2020] Disp R-CNN: Stereo 3D Object Detection via Shape Prior Guided Instance Disparity Estimation [pytorch]
• [Arxiv] SSN: Shape Signature Networks for Multi-class Object Detection from Point Clouds [github]
• [CVPR2020] End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection [github]
• [Arxiv] Finding Your (3D) Center: 3D Object Detection Using a Learned Loss
• [CVPR2020] PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
• [CVPR2020] 3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segm
• [CVPR2020] Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation
• [CVPR2020] OccuSeg: Occupancy-aware 3D Instance Segmentation
• [CVPR2020] Learning to Segment 3D Point Clouds in 2D Image Space
• [CVPR2020] Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud [tensorflow]
• [AAAI2020] ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection
• [Arxiv] MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships
• [Arxiv] HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection
• [Arxiv] SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation
• [Arxiv] 3DSSD: Point-based 3D Single Stage Object Detector
• [Arxiv] Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimation
• [CVPR2020] ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votes
• [Arxiv] A Review on Object Pose Recovery: from 3D Bounding Box Detectors to Full 6D Pose Estimators
• [Arxiv] ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language
• [Arxiv] Objects as Points [github] ⭐🔥
• [Arxiv] RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving [github]
• [CVPR2020] DSGN: Deep Stereo Geometry Network for 3D Object Detection [github]
• [Arxiv] Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation
• [Arxiv] PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
• [Arxiv] Object as Hotspots: An Anchor-Free 3D Object Detection Approach via Firing of Hotspots
• [CVPR2020] SESS: Self-Ensembling Semi-Supervised 3D Object Detection
• [NeurIPS2019] PerspectiveNet: 3D Object Detection from a Single RGB Image via Perspective Points
• [NeurIPS2019] Learning Object Bounding Boxes for 3D Instance Segmentation on Point Clouds
• [ICCV2019] Deep Hough Voting for 3D Object Detection in Point Clouds
• [AAAI2020] JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds
• [ICCV2019] M3D-RPN: Monocular 3D Region Proposal Network for Object Detection [pytorch]
• [ICCV2019] 3D Instance Segmentation via Multi-Task Metric Learning
• [Arxiv] Single-Stage Monocular 3D Object Detection with Virtual Cameras
• [Arxiv] Depth Completion via Deep Basis Fitting
• [Arxiv] Relation Graph Network for 3D Object Detection in Point Clouds
• [CVPR2019] 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans [pytorch] 🔥
• [ICCV2019] Rescan: Inductive Instance Segmentation for Indoor RGBD Scans [C++]
• [ICCV2019] Transferable Semi-Supervised 3D Object Detection From RGB-D Data
• [ICCV2019] STD: Sparse-to-Dense 3D Object Detector for Point Cloud
• [CVPR2019] PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud [pytorch]
• [Arxiv] Fast Point R-CNN
• [Arxiv] Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection [pytorch] 🔥
• [ECCV2018] 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation [pytorch] 🔥

• [Arxiv] A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation [Project]
• [Arxiv] ShapeMOD: Macro Operation Discovery for 3D Shape Programs [Project]
• [Arxiv] CoCoNets: Continuous Contrastive 3D Scene Representations [Project]
• [Arxiv] DeepMetaHandles: Learning Deformation Meta-Handles of 3D Meshes with Biharmonic Coordinates [Project]

• [Arxiv] Point2Skeleton: Learning Skeletal Representations from Point Clouds [pytorch]
• [Arxiv] ParaNet: Deep Regular Representation for 3D Point Clouds
• [Arxiv] Geometric Adversarial Attacks and Defenses on 3D Point Clouds [tensorflow]
• [Arxiv] Learning Category-level Shape Saliency via Deep Implicit Surface Networks
• [Arxiv] pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis
• [Arxiv] Deep Implicit Templates for 3D Shape Representation
• [NeurIPS2020] MetaSDF: Meta-learning Signed Distance Functions [Project]
• [Arxiv] RISA-Net: Rotation-Invariant Structure-Aware Network for Fine-Grained 3D Shape Retrieval [tensorflow]
• [Arxiv] Overfit Neural Networks as a Compact Shape Representation
• [Arxiv] DSM-Net: Disentangled Structured Mesh Net for Controllable Generation of Fine Geometry [Project]
• [Arxiv] PatchNets: Patch-Based Generalizable Deep Implicit 3D Shape Representations
• [Arxiv] CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations
• [Arxiv] ROCNET: RECURSIVE OCTREE NETWORK FOR EFFICIENT 3D DEEP REPRESENTATION
• [ECCV2020] GeLaTO: Generative Latent Textured Objects [Project]
• [ECCV2020] Ladybird: Quasi-Monte Carlo Sampling for Deep Implicit Field Based 3D Reconstruction with Symmetry
• [Arxiv] Neural Sparse Voxel Fields
• [CVPR2020] StructEdit: Learning Structural Shape Variations [github]
• [Arxiv] PAI-GCN: Permutable Anisotropic Graph Convolutional Networks for 3D Shape Representation Learning [github]
• [CVPR2020] Learning Generative Models of Shape Handles [Project page]
• [CVPR2020] DualSDF: Semantic Shape Manipulation using a Two-Level Representation [github]
• [CVPR2020] Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image [pytorch]
• [NeurIPS2019] Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations [pytorch]
• [Arxiv] Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions
• [Arxiv] Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds
• [Arxiv] Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction
• [Arxiv] SeqXY2SeqZ: Structure Learning for 3D Shapes by Sequentially Predicting 1D Occupancy Segments From 2D Coordinates
• [CVPR2020] D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
• [Arxiv] Implicit Geometric Regularization for Learning Shapes
• [Arxiv] Analytic Marching: An Analytic Meshing Solution from Deep Implicit Surface Networks
• [Arxiv] Adversarial Generation of Continuous Implicit Shape Representations [pytorch]
• [Arxiv] A Novel Tree-structured Point Cloud Dataset For Skeletonization Algorithm Evaluation [dataset]
• [CVPRW2019] SkelNetOn 2019: Dataset and Challenge on Deep Learning for Geometric Shape Understanding [project]
• [Arxiv] Skeleton Extraction from 3D Point Clouds by Decomposing the Object into Parts
• [Arxiv] InSphereNet: a Concise Representation and Classification Method for 3D Object
• [Arxiv] Deep Structured Implicit Functions
• [CVIU] 3D articulated skeleton extraction using a single consumer-grade depth camera
• [ICLR2019] Point Cloud GAN [tensorflow]
• [ICCV2019] Learning Shape Templates with Structured Implicit Functions
• [ICCV2019] 3D Point Cloud Generative Adversarial Network Based on Tree Structured Graph Convolutions [pytorch]
• [ICCV2019] Implicit Surface Representations as Layers in Neural Networks
• [CVPR2019] DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation [pytorch] 🔥 ⭐
• [SIGGRAPH2019] StructureNet: Hierarchical Graph Networks for 3D Shape Generation [pytorch]
• [SIGGRAPH Asia2019] LOGAN: Unpaired Shape Transform in Latent Overcomplete Space [tensorflow]
• [TOG] Voxel Cores: Efficient, robust, and provably good approximation of 3D medial axes
• [SIGGRAPH2018] P2P-NET: Bidirectional Point Displacement Net for Shape Transform [tensorflow]
• [ICML2018] Learning Representations and Generative Models for 3D Point Clouds [tensorflow] 🔥⭐
• [NeurIPS2018] Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning [tensorflow][project page]:star::fire:
• [AAAI2018] Unsupervised Articulated Skeleton Extraction from Point Set Sequences Captured by a Single Depth Camera
• [3DV2018] Parsing Geometry Using Structure-Aware Shape Templates
• [SIGGRAPH2017] GRASS: Generative Recursive Autoencoders for Shape Structures [pytorch] 🔥
• [TOG] Erosion Thickness on Medial Axes of 3D Shapes
• [Vis Comput] Distance field guided L1-median skeleton extraction
• [CGF] Contracting Medial Surfaces Isotropically for Fast Extraction of Centred Curve Skeletons
• [CGF] Improved Use of LOP for Curve Skeleton Extraction
• [SIGGRAPH Asia2015] Deep Points Consolidation [C++ & Qt]
• [SIGGRAPH2015] Burning The Medial Axis
• [SIGGRAPH2009] Curve Skeleton Extraction from Incomplete Point Cloud [matlab] ⭐
• [TOG] SDM-NET: deep generative network for structured deformable mesh
• [TOG] Robust and Accurate Skeletal Rigging from Mesh Sequences 🔥
• [TOG] L₁-medial skeleton of point cloud [C++] 🔥
• [EUROGRAPHICS2016] 3D Skeletons: A State-of-the-Art Report 🔥
• [SGP2012] Mean Curvature Skeletons [C++] 🔥
• [SMIC2010] Point Cloud Skeletons via Laplacian-Based Contraction [Matlab] 🔥

• [CVPR2021] Point Cloud Upsampling via Disentangled Refinement [github]
• [TVCG2021] Consistent Two-Flow Network for Tele-Registration of Point Clouds [Project]
• [Arxiv] 4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface [Project]
• [CVPR2021] Unsupervised 3D Shape Completion through GAN Inversion [Project]
• [Arxiv] ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point Completion
• [CVPR2021] Variational Relational Point Completion Network [Project]
• [CVPR2021] View-Guided Point Cloud Completion
• [CVPR2021] Semantic Scene Completion via Integrating Instances and Scene in-the-Loop [pytorch]
• [CVPR2021] Denoise and Contrast for Category Agnostic Shape Completion
• [CVPR2021] Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Coding
• [CVPR2021] PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Paths
• [CVPR2021] Style-based Point Generator with Adversarial Rendering for Point Cloud Completion

• [Arxiv] PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Paths
• [Arxiv] S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds
• [Arxiv] Semantic Scene Completion using Local Deep Implicit Functions on LiDAR Data
• [Arxiv] Learning-based 3D Occupancy Prediction for Autonomous Navigation in Occluded Environments
• [Arxiv] PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving Paths
• [3DV2020] SCFusion: Real-time Incremental Scene Reconstruction with Semantic Completion
• [Arxiv] Refinement of Predicted Missing Parts Enhance Point Cloud Completion [pytorch]
• [Arxiv] Unsupervised Partial Point Set Registration via Joint Shape Completion and Registration
• [Arxiv] LMSCNet: Lightweight Multiscale 3D Semantic Completion [Demo]
• [ECCV2020] SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification
• [ECCV2020] Weakly-supervised 3D Shape Completion in the Wild
• [Arxiv] Point Cloud Completion by Learning Shape Priors
• [Arxiv] KAPLAN: A 3D Point Descriptor for Shape Completion
• [Arxiv] VPC-Net: Completion of 3D Vehicles from MLS Point Clouds
• [Arxiv] SPSG: Self-Supervised Photometric Scene Generation from RGB-D Scans
• [Arxiv] GRNet: Gridding Residual Network for Dense Point Cloud Completion
• [Arxiv] Deep Octree-based CNNs with Output-Guided Skip Connections for 3D Shape and Scene Completion
• [CVPR2020] Point Cloud Completion by Skip-attention Network with Hierarchical Folding
• [CVPR2020] Cascaded Refinement Network for Point Cloud Completion [github]
• [CVPR2020] Anisotropic Convolutional Networks for 3D Semantic Scene Completion [github]
• [AAAI2020] Attention-based Multi-modal Fusion Network for Semantic Scene Completion
• [CVPR2020] 3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior [github]
• [ECCV2020] Multimodal Shape Completion via Conditional Generative Adversarial Networks [pytorch]
• [CVPR2020] RevealNet: Seeing Behind Objects in RGB-D Scans
• [CVPR2020] Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion
• [CVPR2020] PF-Net: Point Fractal Network for 3D Point Cloud Completion
• [Arxiv] 3D Gated Recurrent Fusion for Semantic Scene Completion
• [ICCVW2019] EdgeConnect: Structure Guided Image Inpainting using Edge Prediction [pytorch] 🔥⭐
• [ICRA2020] Depth Based Semantic Scene Completion with Position Importance Aware Loss
• [CVPR2020] SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans
• [Arxiv] PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes
• [ICLR2020] Unpaired Point Cloud Completion on Real Scans using Adversarial Training [tensorflow]
• [AAAI2020] Morphing and Sampling Network for Dense Point Cloud Completion [pytorch]
• [ICCVW2019] Render4Completion: Synthesizing Multi-View Depth Maps for 3D Shape Completion
• [ICCV2019] ForkNet: Multi-branch Volumetric Semantic Completion from a Single Depth Image [tensorflow]
• [ICCV2019] Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion [Caffe3D]
• [ICCV2019] 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] EdgeNet: Semantic Scene Completion from RGB-D images
• [CVPR2019] TopNet: Structural Point Cloud Decoder [pytorch & tensorflow]
• [CVPR2019] Deep Reinforcement Learning of Volume-guided Progressive View Inpainting for 3D Point Scene Completion from a Single Depth Image
• [CVPR2019] Leveraging Shape Completion for 3D Siamese Tracking [pytorch]
• [CVPR2019] RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completion [pytorch]
• [3DV2018] PCN: Point Completion Network [tensorflow] 🔥
• [ECCV2018] Efficient Semantic Scene Completion Network with Spatial Group Convolution [pytorch]
• [CVPR2018] ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans [tensorflow] 🔥⭐
• [CVPR2018] Learning 3D Shape Completion from Laser Scan Data with Weak Supervision [torch][torch]
• [IJCV2018] Learning 3D Shape Completion under Weak Supervision [torch][torch]
• [ICCV2017] High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference ⭐
• [ICCV2017] Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis [torch] 🔥⭐
• [CVPR2017] Semantic Scene Completion from a Single Depth Image [caffe] 🔥⭐
• [CVPR2016] Structured Prediction of Unobserved Voxels From a Single Depth Image [resource] ⭐

• [Arxiv] View Generalization for Single Image Textured 3D Models [Project]
• [Arxiv] Shape As Points: A Differentiable Poisson Solver
• [Arxiv] Neural Implicit 3D Shapes from Single Images with Spatial Patterns
• [IJCAI2021] Spline Positional Encoding for Learning 3D Implicit Signed Distance Fields
• [Arxiv] Z2P: Instant Rendering of Point Clouds
• [CVPR2021] Multi-view 3D Reconstruction of a Texture-less Smooth Surface of Unknown Generic Reflectance
• [CVPR2021] Birds of a Feather: Capturing Avian Shape Models from Images [Project]
• [Arxiv] DeepCAD: A Deep Generative Network for Computer-Aided Design Models
• [Arxiv] StrobeNet: Category-Level Multiview Reconstruction of Articulated Objects
• [CVPR2021] Sketch2Model: View-Aware 3D Modeling from Single Free-Hand Sketches
• [Arxiv] Sign-Agnostic CONet: Learning Implicit Surface Reconstructions by Sign-Agnostic Optimization of Convolutional Occupancy Networks
• [IJCAI2021] PointLIE: Locally Invertible Embedding for Point Cloud Sampling and Recovery
• [Arxiv] UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction
• [CVPR2021] Shape and Material Capture at Home
• [CVPR2021] StereoPIFu: Depth Aware Clothed Human Digitization via Stereo Vision [Project]
• [Arxiv] CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assembly
• [CVPR2021] Fully Understanding Generic Objects: Modeling, Segmentation, and Reconstruction [Project]
• [CVPR2021] Online Learning of a Probabilistic and Adaptive Scene Representation
• [CVPR2021] Fostering Generalization in Single-view 3D Reconstruction by Learning a Hierarchy of Local and Global Shape Priors
• [Arxiv] Sketch2Mesh: Reconstructing and Editing 3D Shapes from Sketches
• [CVPR2021] Deep Implicit Moving Least-Squares Functions for 3D Reconstruction [Project]
• [Arxiv] PC2WF: 3D WIREFRAME RECONSTRUCTION FROM RAW POINT CLOUDS
• [CVPR2021] Diffusion Probabilistic Models for 3D Point Cloud Generation [Project]
• [Arxiv] ShaRF: Shape-conditioned Radiance Fields from a Single View [Project]
• [Arxiv] Shelf-Supervised Mesh Prediction in the Wild
• [Arxiv] HyperPocket: Generative Point Cloud Completion
• [Arxiv] Im2Vec: Synthesizing Vector Graphics without Vector Supervision [resource]
• [Arxiv] Secrets of 3D Implicit Object Shape Reconstruction in the Wild
• [Arxiv] Joint Learning of 3D Shape Retrieval and Deformation
• [Arxiv] Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes

• [Arxiv] Learning Delaunay Surface Elements for Mesh Reconstruction
• [Arxiv] Compositionally Generalizable 3D Structure Prediction
• [Arxiv] Online Adaptation for Consistent Mesh Reconstruction in the Wild
• [Arxiv] Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction from Raw Point Clouds
• [Arxiv] Deep Optimized Priors for 3D Shape Modeling and Reconstruction
• [Arxiv] DO 2D GANS KNOW 3D SHAPE? UNSUPERVISED 3D SHAPE RECONSTRUCTION FROM 2D IMAGE GANS [Project]
• [Arxiv] DUDE: Deep Unsigned Distance Embeddings for Hi-Fidelity Representation of Complex 3D Surfaces
• [3DV2020] Learning to Infer Semantic Parameters for 3D Shape Editing [Project]
• [3DV2020] Cycle-Consistent Generative Rendering for 2D-3D Modality Translation [Project]
• [3DV2020] A Divide et Impera Approach for 3D Shape Reconstruction from Multiple Views
• [Arxiv] A Closed-Form Solution to Local Non-Rigid Structure-from-Motion
• [Arxiv] Deformed Implicit Field: Modeling 3D Shapes with Learned Dense Correspondence
• [Arxiv] D-NeRF: Neural Radiance Fields for Dynamic Scenes
• [Arxiv] Modular Primitives for High-Performance Differentiable Rendering
• [Arxiv] NeuralFusion: Online Depth Fusion in Latent Space
• [Arxiv] Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Deforming Scene from Monocular Video [Project]
• [NeurIPS2020] Continuous Object Representation Networks: Novel View Synthesis without Target View Supervision [Project]
• [NeurIPS2020] SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images [Project]
• [NeurIPS2020] Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance [Project]
• [NeurIPS2020] Convolutional Generation of Textured 3D Meshes [Project]
• [Arxiv] Vid2CAD: CAD Model Alignment using Multi-View Constraints from Videos
• [NeurIPS2020] UCLID-Net: Single View Reconstruction in Objec Space [Project]
• [NeurIPS2020] CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations [Project]
• [NeurIPS2020] Generative 3D Part Assembly via Dynamic Graph Learning [pytorch]
• [NeurIPS2020] Learning Deformable Tetrahedral Meshes for 3D Reconstruction [Project]
• [NeurIPS2020] SoftFlow: Probabilistic Framework for Normalizing Flow on Manifolds [pytorch]
• [Arxiv] Training Data Generating Networks: Linking 3D Shapes and Few-Shot Classification
• [Arxiv] MESHMVS: MULTI-VIEW STEREO GUIDED MESH RECONSTRUCTION
• [Arxiv] Learning Occupancy Function from Point Clouds for Surface Reconstruction
• [NeurIPS2020] SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images [Project]
• [Arxiv] GRF: Learning a General Radiance Field for 3D Scene Representation and Rendering [github]
• [3DV2020] A Progressive Conditional Generative Adversarial Network for Generating Dense and Colored 3D Point Clouds
• [3DV2020] Better Patch Stitching for Parametric Surface Reconstruction
• [NeurIPS2020] Skeleton-bridged Point Completion: From Global Inference to Local Adjustment [Project Page]
• [Arxiv] NeRF++: Analyzing and Improving Neural Radiance Fields [pytorch]
• [Arxiv] Improved Modeling of 3D Shapes with Multi-view Depth Maps
• [SIGGRAPH2020] One Shot 3D Photography [Project]
• [BMVC2020] Large Scale Photometric Bundle Adjustment
• [ECCV2020] Interactive Annotation of 3D Object Geometry using 2D Scribbles [Project]
• [BMVC2020] Visibility-aware Multi-view Stereo Network
• [ECCV2020] Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images
• [ECCV2020] 3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View [Project][Pytorch]
• [BMVC2020] 3D-GMNet: Single-View 3D Shape Recovery as A Gaussian Mixture
• [SIGGRAPH2020] Self-Sampling for Neural Point Cloud Consolidation
• [ECCV2020] Stochastic Bundle Adjustment for Efficient and Scalable 3D Reconstruction [github]
• [Arxiv] NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections [Project]
• [Arxiv] MeshODE: A Robust and Scalable Framework for Mesh Deformation
• [Arxiv] MRGAN: Multi-Rooted 3D Shape Generation with Unsupervised Part Disentanglement
• [ECCV2020] Meshing Point Clouds with Predicted Intrinsic-Extrinsic Ratio Guidance [pytorch]
• [ECCV2020] Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop
• [ECCV2020] Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking
• [ECCV2020] Shape and Viewpoint without Keypoints
• [Arxiv] Object-Centric Multi-View Aggregation
• [ECCV2020] Points2Surf Learning Implicit Surfaces from Point Clouds
• [NeurIPS2020] Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows [Project]
• [Arxiv] Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images
• [Arxiv] Neural Non-Rigid Tracking
• [NeurIPS2020] MeshSDF: Differentiable Iso-Surface Extraction
• [Arxiv] 3D Reconstruction of Novel Object Shapes from Single Images
• [NeurIPS2020] ShapeFlow: Learnable Deformations Among 3D Shapes [pytorch]
• [Arxiv] 3D Shape Reconstruction from Free-Hand Sketches
• [Arxiv] Convolutional Occupancy Networks
• [Siggraph2020] Point2Mesh: A Self-Prior for Deformable Meshes
• [Arxiv] PointTriNet: Learned Triangulation of 3D Point
• [Arxiv] A Simple and Scalable Shape Representation for 3D Reconstruction
• [Siggraph2020] Vid2Curve: Simultaneously Camera Motion Estimation and Thin Structure Reconstruction from an RGB Video
• [CVPR2020] From Image Collections to Point Clouds with Self-supervised Shape and Pose Networks [tensorflow]
• [CVPR2020] Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes [github]
• [Arxiv] PolyGen: An Autoregressive Generative Model of 3D Meshes
• [Arxiv] Combinatorial 3D Shape Generation via Sequential Assembly
• [Arxiv] Few-Shot Single-View 3-D Object Reconstruction with Compositional Priors
• [Arxiv] Neural Object Descriptors for Multi-View Shape Reconstruction
• [CVPR2020] SPARE3D: A Dataset for SPAtial REasoning on Three-View Line Drawings [pytorch]
• [Arxiv] Modeling 3D Shapes by Reinforcement Learning
• [ECCV2020] ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds [pytorch]
• [Arxiv] Self-Supervised 2D Image to 3D Shape Translation with Disentangled Representations
• [Arxiv] Universal Differentiable Renderer for Implicit Neural Representations
• [Arxiv] Learning 3D Part Assembly from a Single Image
• [Arxiv] Curriculum DeepSDF
• [Arxiv] PT2PC: Learning to Generate 3D Point Cloud Shapes from Part Tree Conditions
• [Arxiv] Self-supervised Single-view 3D Reconstruction via Semantic Consistency
• [Arxiv] Meta3D: Single-View 3D Object Reconstruction from Shape Priors in Memory
• [Arxiv] STD-Net: Structure-preserving and Topology-adaptive Deformation Network for 3D Reconstruction from a Single Image
• [Arxiv] Curvature Regularized Surface Reconstruction from Point Cloud
• [Arxiv] Hypernetwork approach to generating point clouds
• [Arxiv] Inverse Graphics GAN: Learning to Generate 3D Shapes from Unstructured 2D Data
• [Arxiv] Meshlet Priors for 3D Mesh Reconstruction
• [Arxiv] Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction
• [Arxiv] SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization
• [CVPR2019] Occupancy Networks: Learning 3D Reconstruction in Function Space [pytorch] 🔥⭐
• [NeurIPS2019] DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction [tensorflow]
• [NeurIPS2019] Learning to Infer Implicit Surfaces without 3D Supervision
• [CVPR2019] A Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Images [pytorch & tensorflow]
• [Arxiv] Deep Level Sets: Implicit Surface Representations for 3D Shape Inference
• [CVPR2019] Learning Implicit Fields for Generative Shape Modeling [tensorflow] 🔥
• [ICCV2019] Point-based Multi-view Stereo Network [pytorch] ⭐
• [Arxiv] TSRNet: Scalable 3D Surface Reconstruction Network for Point Clouds using Tangent Convolution
• [Arxiv] DR-KFD: A Differentiable Visual Metric for 3D Shape Reconstruction
• [ICCV2019] GraphX-Convolution for Point Cloud Deformation in 2D-to-3D Conversion
• [ICCV2019] Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformation [pytorch]
• [ICCV2019] Few-Shot Generalization for Single-Image 3D Reconstruction via Priors
• [ICCV2019] Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networks
• [AAAI2018] Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction [tensorflow] ⭐🔥
• [NeurIPS2017] MarrNet: 3D Shape Reconstruction via 2.5D Sketches [torch]:star::fire:

• [ICRA2021] Efficient and Robust LiDAR-Based End-to-End Navigation [Project]
• [ICLR2021] VTNet: Visual Transformer Network for Object Goal Navigation
• [CVPR2021] Self-Point-Flow: Self-Supervised Scene Flow Estimation from Point Clouds with Optimal Transport and Random Walk
• [CVPR2021] HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embedding
• [Arxiv] FloorPlanCAD: A Large-Scale CAD Drawing Dataset for Panoptic Symbol Spotting
• [Arxiv] SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation
• [Arxiv] Collision Replay: What Does Bumping Into Things Tell You About Scene Geometry? [Project]
• [Arxiv] Pri3D: Can 3D Priors Help 2D Representation Learning?
• [Arxiv] LaLaLoc: Latent Layout Localisation in Dynamic, Unvisited Environments
• [CVPRW] OmniLayout: Room Layout Reconstruction from Indoor Spherical Panoramas [github]
• [Arxiv] Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image [pytorch]
• [Arxiv] SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds with 1000× Fewer Labels [github]
• [CVPR2021] FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point Clouds
• [CVPR2021] Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud [github]
• [ICRA] Reconstructing Interactive 3D Scenes by Panoptic Mapping and CAD Model Alignments [Project]
• [Arxiv] Contextual Scene Augmentation and Synthesis via GSACNet
• [Arxiv] In-Place Scene Labelling and Understanding with Implicit Scene Representation
• [CVPR2021] Bidirectional Projection Network for Cross Dimension Scene Understanding [github]
• [Arxiv] Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud [github]
• [CVPR2021] Visual Room Rearrangement [Project]
• [Arxiv] MonteFloor: Extending MCTS for Reconstructing Accurate Large-Scale Floor Plans
• [Arxiv] Structured Scene Memory for Vision-Language Navigation
• [Arxiv] House-GAN++: Generative Adversarial Layout Refinement Networks
• [Arxiv] Weakly Supervised Learning of Rigid 3D Scene Flow
• [ICLR2021] End-to-End Egospheric Spatial Memory
• [Arxiv] Single-Shot Cuboids: Geodesics-based End-to-end Manhattan Aligned Layout Estimation from Spherical Panoramas [Project]
• [Arxiv] A modular vision language navigation and manipulation framework for long horizon compositional tasks in indoor environment
• [Arxiv] Deep Reinforcement Learning for Producing Furniture Layout in Indoor Scenes
• [Arxiv] Where2Act: From Pixels to Actions for Articulated 3D Objects [Project]

• [Arxiv] AI2-THOR: An Interactive 3D Environment for Visual AI [Project]
• [Arxiv] Audio-Visual Floorplan Reconstruction
• [Arxiv] PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds
• [Arxiv] RAFT-3D: Scene Flow using Rigid-Motion Embeddings
• [Arxiv] GenScan: A Generative Method for Populating Parametric 3D Scan Datasets
• [Arxiv] LayoutGMN: Neural Graph Matching for Structural Layout Similarity
• [Arxiv] Seeing Behind Objects for 3D Multi-Object Tracking in RGB-D Sequences
• [Arxiv] P4Contrast: Contrastive Learning with Pairs of Point-Pixel Pairs for RGB-D Scene Understanding
• [Arxiv] Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net
• [Arxiv] Localising In Complex Scenes Using Balanced Adversarial Adaptation
• [Arxiv] Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis
• [NeurIPS2020] Multi-Plane Program Induction with 3D Box Priors [Project]
• [Arxiv] HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features
• [Arxiv] Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts
• [Arxiv] Generative Layout Modeling using Constraint Graphs
• [NeurIPS2020] Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D [pytorch]
• [NeurIPS2020] Learning Affordance Landscapes for Interaction Exploration in 3D Environments [Project]
• [NeurIPS2020W] Unsupervised Domain Adaptation for Visual Navigation
• [Arxiv] Embodied Visual Navigation with Automatic Curriculum Learningin Real Environments
• [Arxiv] 3D Room Layout Estimation Beyond the Manhattan World Assumption
• [Arxiv] OpenBot: Turning Smartphones into Robots [Project]
• [Arxiv] Audio-Visual Waypoints for Navigation
• [Arxiv] Learning Affordance Landscapes for Interaction Exploration in 3D Environments [Project]
• [ECCV2020] Occupancy Anticipation for Efficient Exploration and Navigation [Project]
• [Arxiv] Retargetable AR: Context-aware Augmented Reality in Indoor Scenes based on 3D Scene Graph
• [Arxiv] Generating Person-Scene Interactions in 3D Scenes
• [Arxiv] GeoLayout: Geometry Driven Room Layout Estimation Based on Depth Maps of Planes
• [ECCV2020] ReferIt3D: Neural Listeners for Fine-Grained 3D Object Identification in Real-World Scenes
• [Arxiv] Structural Plan of Indoor Scenes with Personalized Preferences
• [Arxiv] HoliCity: A City-Scale Data Platform for Learning Holistic 3D Structures [Project]
• [CVPR2020] End-to-End Optimization of Scene Layout [Project]
• [Arxiv] Improving Target-driven Visual Navigation with Attention on 3D Spatial Relationships
• [CVPR2020] Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions
• [Arxiv] LayoutMP3D: Layout Annotation of Matterport3D
• [CVPR2020] Local Implicit Grid Representations for 3D Scenes
• [Arxiv] Scan2Plan: Efficient Floorplan Generation from 3D Scans of Indoor Scenes
• [CVPR2020] RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds [tensorflow] 🔥
• [CVPR2020] Intelligent Home 3D: Automatic 3D-House Design from Linguistic Descriptions Only
• [ICRA2020] 3DCFS: Fast and Robust Joint 3D Semantic-Instance Segmentation via Coupled Feature Selection
• [Arxiv] Indoor Scene Recognition in 3D
• [Journal] Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense
• [Arxiv] BlockGAN Learning 3D Object-aware Scene Representations from Unlabelled Images
• [Arxiv] 3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans [Project] Related: [Arxiv] [Arxiv]
• [ICCV2019] U4D: Unsupervised 4D Dynamic Scene Understanding
• [ICCV2019] UprightNet: Geometry-Aware Camera Orientation Estimation from Single Images
• [ICCV2019] Habitat: A Platform for Embodied AI Research [habitat-api] [habitat-sim] ⭐
• [ICCV2019] SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences [project page] ⭐
• [ICCV2019] Neural Inverse Rendering of an Indoor Scene From a Single Image
• [ICCV2019] SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentation [pytorch]
• [ICCV2019] RIO: 3D Object Instance Re-Localization in Changing Indoor Environments [dataset]
• [ICCV2019] CamNet: Coarse-to-Fine Retrieval for Camera Re-Localization
• [ICCV2019] U4D: Unsupervised 4D Dynamic Scene Understanding
• [NeurIPS2018] Learning to Exploit Stability for 3D Scene Parsing

• [CVPR2021] Plan2Scene: Converting Floorplans to 3D Scenes [Project]
• [Arxiv] Translational Symmetry-Aware Facade Parsing for 3D Building Reconstruction
• [Arxiv] Learning to Stylize Novel Views [Project]
• [Arxiv] Stylizing 3D Scene via Implicit Representation and HyperNetwork
• [CVPR2021] SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction from Video Data [Project]
• [Arxiv] The Boombox: Visual Reconstruction from Acoustic Vibrations [Project]
• [Arxiv] Joint Pose and Shape Estimation of Vehicles from LiDAR Data
• [CVPR2021] NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video [Project]
• [Arxiv] DDR-Net: Learning Multi-Stage Multi-View Stereo With Dynamic Depth Range [pytorch]
• [Arxiv] Planar Surface Reconstruction from Sparse Views [Project]
• [Arxiv] Neural RGB-D Surface Reconstruction
• [Arxiv] RetrievalFuse: Neural 3D Scene Reconstruction with a Database
• [Arxiv] PlenOctrees for Real-time Rendering of Neural Radiance Fields [C++]
• [Arxiv] iMAP: Implicit Mapping and Positioning in Real-Time
• [CVPR2021] Monte Carlo Scene Search for 3D Scene Understanding
• [CVPR2021] Holistic 3D Scene Understanding from a Single Image with Implicit Representation
• [CVPR2021] RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction [pytorch]
• [Arxiv] IBRNet: Learning Multi-View Image-Based Rendering [Project]
• [Arxiv] STaR: Self-supervised Tracking and Reconstruction of Rigid Objects in Motion with Neural Rendering [Project]

• [Arxiv] MO-LTR: Multiple Object Localization, Tracking and Reconstruction from Monocular RGB Videos
• [Arxiv] DI-Fusion: Online Implicit 3D Reconstruction with Deep Priors
• [3DV2020] Scene Flow from Point Clouds with or without Learning
• [Arxiv] Stable View Synthesis
• [Arxiv] Neural Scene Graphs for Dynamic Scenes
• [3DV2020] RidgeSfM: Structure from Motion via Robust Pairwise Matching Under Depth Uncertainty [pytorch]
• [Arxiv] FlowStep3D: Model Unrolling for Self-Supervised Scene Flow Estimation
• [Arxiv] MoNet: Motion-based Point Cloud Prediction Network
• [Arxiv] MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera
• [Arxiv] Efficient Initial Pose-graph Generation for Global SfM
• [Arxiv] Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes [Project]
• [Arxiv] RGBD-Net: Predicting color and depth images for novel views synthesis
• [Arxiv] SSCNav: Confidence-Aware Semantic Scene Completion for Visual Semantic Navigation [Project]
• [Arxiv] From Points to Multi-Object 3D Reconstruction
• [Arxiv] Worldsheet: Wrapping the World in a 3D Sheet for View Synthesis from a Single Image [Project]
• [Arxiv] SceneFormer: Indoor Scene Generation with Transformers [pytorch]
• [NeurIPS2020] Neural Sparse Voxel Fields [Project]
• [Arxiv] Towards Part-Based Understanding of RGB-D Scans
• [Arxiv] Dynamic Plane Convolutional Occupancy Networks
• [NeurIPS2020] Neural Unsigned Distance Fields for Implicit Function Learning [Project]
• [Arxiv] Holistic static and animated 3D scene generation from diverse text descriptions [pytorch]
• [Arxiv] Semi-Supervised Learning of Multi-Object 3D Scene Representations
• [ECCV2020] CAD-Deform: Deformable Fitting of CAD Models to 3D Scans
• [ECCV2020] Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve
• [ECCV2020] Learnable Cost Volume Using the Cayley Representation
• [ECCV2020] Topology-Change-Aware Volumetric Fusion for Dynamic Scene Reconstruction
• [ECCV2020] Convolutional Occupancy Networks
• [CVPR2020] MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction
• [ECCV2020] CoReNet: Coherent 3D scene reconstruction from a single RGB image
• [CVPR2020] DOPS: Learning to Detect 3D Objects and Predict their 3D Shapes
• [ECCV2020] SceneCAD: Predicting Object Alignments and Layouts in RGB-D Scans
• [Arxiv] Removing Dynamic Objects for Static Scene Reconstruction using Light Fields
• [Arxiv] Atlas: End-to-End 3D Scene Reconstruction from Posed Images
• [Arxiv] Scan2Plan: Efficient Floorplan Generation from 3D Scans of Indoor Scenes
• [Arxiv] Plane Pair Matching for Efficient 3D View Registration
• [CVPR2020] Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image [pytorch]
• [Arxiv] Indoor Layout Estimation by 2D LiDAR and Camera Fusion
• [Arxiv] General 3D Room Layout from a Single View by Render-and-Compare
• [ICCV2019] Learning to Reconstruct 3D Manhattan Wireframes from a Single Image
• [CVPR2019] PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image [pytorch]:fire:
• [ICCV2019] 3D Scene Reconstruction with Multi-layer Depth and Epipolar Transformers
• [ICCV Workshop2019] Silhouette-Assisted 3D Object Instance Reconstruction from a Cluttered Scene
• [ICCV2019] 3D-RelNet: Joint Object and Relation Network for 3D prediction [pytorch]
• [3DV2019] Pano Popups: Indoor 3D Reconstruction with a Plane-Aware Network
• [CVPR2018] Factoring Shape, Pose, and Layout from the 2D Image of a 3D Scene [pytorch]
• [IROS2017] Indoor Scan2BIM: Building Information Models of House Interiors
• [CVPR2017] 3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions [github]

• [Arxiv] NeRF in detail: Learning to sample for view synthesis
• [Arxiv] NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination [Project]
• [Arxiv] Neural Trajectory Fields for Dynamic Novel View Synthesis
• [Arxiv] Editing Conditional Radiance Fields [Project]
• [CVPR2021] Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenes
• [Arxiv] GNeRF: GAN-based Neural Radiance Field without Posed Camera
• [Arxiv] BARF: Bundle-Adjusting Neural Radiance Fields [Project]
• [Arxiv] MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo
• [CVPR2021] Neural Lumigraph Rendering [Project]
• [Arxiv] Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields
• [Arxiv] KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs
• [Arxiv] FastNeRF: High-Fidelity Neural Rendering at 200FPS
• [CVPR2021] NeX: Real-time View Synthesis with Neural Basis Expansion [Project]
• [Arxiv] DONeRF: Towards Real-Time Rendering of Neural Radiance Fields using Depth Oracle Networks [Project]
• [Arxiv] NeRF--: Neural Radiance Fields Without Known Camera Parameters [Project]

• [Arxiv] pixelNeRF: Neural Radiance Fields from One or Few Images [Project]
• [Arxiv] NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis [Project]
• [Arxiv] Neural Radiance Flow for 4D View Synthesis and Video Processing [Project]
• [Arxiv] Deformable Neural Radiance Fields [Project]
• [Arxiv] DeRF: Decomposed Radiance Fields
• [Arxiv] NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis

• [Arxiv] Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control
• [Arxiv] Scene-aware Generative Network for Human Motion Synthesis
• [Arxiv] Human Motion Prediction Using Manifold-Aware Wasserstein GAN
• [CVPR2021] Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors [Project]
• [Arxiv] TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild [Project]
• [CVPR2021] We are More than Our Joints: Predicting how 3D Bodies Move [Project]
• [CVPR2021] LEAP: Learning Articulated Occupancy of People [Project]
• [Arxiv] 3DCrowdNet: 2D Human Pose-Guided 3D Crowd Human Pose and Shape Estimation in the Wild
• [CVPR2021] SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements [Project]
• [Arxiv] Action-Conditioned 3D Human Motion Synthesis with Transformer VAE [Project]
• [Arxiv] Dynamic Surface Function Networks for Clothed Human Bodies [github]
• [Arxiv] Neural Articulated Radiance Field [github]
• [Arxiv] Mesh Graphormer
• [CVPR2021] SimPoE: Simulated Character Control for 3D Human Pose Estimation [Project]
• [Arxiv] TRAJEVAE - Controllable Human Motion Generation from Trajectories [Project]
• [CVPR2021] Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors [Project]
• [CVPR2021] Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction [Project]
• [CVPR2021] Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstruction [github]
• [Arxiv] Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild
• [Arxiv] 3D Human Pose Estimation with Spatial and Temporal Transformers [pytorch]
• [Arxiv] Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks
• [Arxiv] DanceNet3D: Music Based Dance Generation with Parametric Motion Transformer
• [Arxiv] Aggregated Multi-GANs for Controlled 3D Human Motion Prediction [Project]
• [AAAI] PC-HMR: Pose Calibration for 3D Human Mesh Recovery from 2D Images/Videos
• [Arxiv] NeuralHumanFVV: Real-Time Neural Volumetric Human Performance Rendering using RGB Cameras
• [CVPR2021] SMPLicit: Topology-aware Generative Model for Clothed People [Project]
• [CVPR2021] HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation [pytorch]
• [Arxiv] Single-Shot Motion Completion with Transformer [Project]
• [EG2021] Walk2Map: Extracting Floor Plans from Indoor Walk Trajectories
• [Arxiv] Forecasting Characteristic 3D Poses of Human Actions
• [Arxiv] Capturing Detailed Deformations of Moving Human Bodies
• [Arxiv] A-NeRF: Surface-free Human 3D Pose Refinement via Neural Rendering [Project]
• [Arxiv] Learn to Dance with AIST++: Music Conditioned 3D Dance Generation [Project]
• [Arxiv] S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human Modeling
• [Arxiv] PandaNet : Anchor-Based Single-Shot Multi-Person 3D Pose Estimation
• [Arxiv] Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans [Project]
• [Arxiv] Chasing the Tail in Monocular 3D Human Reconstruction with Prototype Memory
• [3DV2020] PLACE: Proximity Learning of Articulation and Contact in 3D Environments [Project]
• [ICCV2019] Resolving 3D Human Pose Ambiguities with 3D Scene Constraints [Project]

• [ECCV2020] History Repeats Itself: Human Motion Prediction via Motion Attention [pytorch]
• [ECCV2020] 3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning [Project]
• [Arxiv] Synthesizing Long-Term 3D Human Motion and Interaction in 3D Scenes [Project]
• [Arxiv] End-to-End Human Pose and Mesh Reconstruction with Transformers
• [Arxiv] Human Mesh Recovery from Multiple Shots [Project]
• [NeurIPS2020] 3D Multi-bodies: Fitting Sets of Plausible 3D Human Models to Ambiguous Image Data [Project]
• [Arxiv] Holistic 3D Human and Scene Mesh Estimation from Single View Images
• [Arxiv] Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video
• [Arxiv] Pose2Pose: 3D Positional Pose-Guided 3D Rotational Pose Prediction for Expressive 3D Human Pose and Mesh Estimation
• [Arxiv] NeuralAnnot: Neural Annotator for in-the-wild Expressive 3D Human Pose and Mesh Training Sets
• [Arxiv] 4D Human Body Capture from Egocentric Video via 3D Scene Grounding [Project]
• [Arxiv] Populating 3D Scenes by Learning Human-Scene Interaction [Project]
• [ECCV2020] Long-term Human Motion Prediction with Scene Context [Project]
• [Arxiv] Vid2Actor: Free-viewpoint Animatable Person Synthesis from Video in the Wild [Project]
• [Arxiv] ANR: Articulated Neural Rendering for Virtual Avatars
• [Arxiv] Generating 3D People in Scenes without People [Project]
• [ICCV2019] Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense
• [CVPR2019] Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments [Project]
• [TOG2016] Pigraphs: learning interaction snapshots from observations [Project]

• [ICML2021] Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline [pytorch]
• [Arxiv] Deep Medial Fields
• [Arxiv] Subdivision-Based Mesh Convolution Networks [Jittor]
• [Arxiv] VA-GCN: A Vector Attention Graph Convolution Network for learning on Point Clouds [pytorch]
• [Arxiv] Aggregating Nested Transformers
• [Arxiv] Rethinking the Design Principles of Robust Vision Transformer [pytorch]
• [Siggraph2021] Acorn: Adaptive Coordinate Networks for Neural Scene Representation
• [Arxiv] Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis [Project]
• [Arxiv] Pay Attention to MLPs
• [Arxiv] ResMLP: Feedforward networks for image classification with data-efficient training
• [Arxiv] RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition
• [Arxiv] MLP-Mixer: An all-MLP Architecture for Vision
• [Arxiv] Vector Neurons: A General Framework for SO(3)-Equivariant Networks
• [CVPR2021] MongeNet: Efficient Sampler for Geometric Deep Learning [Project]
• [Arxiv] Point Cloud Learning with Transformer
• [Arxiv] Dual Transformer for Point Cloud Analysis
• [Arxiv] AttWalk: Attentive Cross-Walks for Deep Mesh Analysis
• [Arxiv] Learning from 2D: Pixel-to-Point Knowledge Transfer for 3D Pretraining
• [Arxiv] Field Convolutions for Surface CNNs
• [Arxiv] Rethinking Spatial Dimensions of Vision Transformers [pytorch] 🔥
• [CVPR2021] PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds [pytorch]
• [Arxiv] Concentric Spherical GNN for 3D Representation Learning
• [Arxiv] High-Performance Large-Scale Image Recognition Without Normalization
• [Arxiv] Generative Models as Distributions of Functions
• [Arxiv] Point-set Distances for Learning Representations of 3D Point Clouds
• [Arxiv] Compressed Object Detection
• [Arxiv] A linearized framework and a new benchmark for model selection for fine-tuning
• [Arxiv] The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions
• [Arxiv] Self-Supervised Pretraining of 3D Features on any Point-Cloud [pytorch]
• [3DV2020] Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networks

• [ICCV2019] Efficient Learning on Point Clouds with Basis Point Sets [pytorch]
• [CVPR2019] On the Continuity of Rotation Representations in Neural Networks [pytorch]
• [Arxiv] Diffusion is All You Need for Learning on Surfaces
• [Arxiv] SPU-Net: Self-Supervised Point Cloud Upsampling by Coarse-to-Fine Reconstruction with Self-Projection Optimization
• [3DV2020] Rotation-Invariant Point Convolution With Multiple Equivariant Alignments
• [Arxiv] One Point is All You Need: Directional Attention Point for Feature Learning
• [Arxiv] PCT: Point Cloud Transformer
• [Arxiv] Hausdorff Point Convolution with Geometric Priors
• [Arxiv] MARNet: Multi-Abstraction Refinement Network for 3D Point Cloud Analysis [Github]
• [Arxiv] Point Transformer
• [Arxiv] Learning geometry-image representation for 3D point cloud generation
• [Arxiv] Deeper or Wider Networks of Point Clouds with Self-attention?
• [NeurIPS2020] Primal-Dual Mesh Convolutional Neural Networks [pytorch]
• [NeurIPS2020] Rational neural networks [tensorflow]
• [NeurIPS2020] Exchangeable Neural ODE for Set Modeling [Project]
• [NeurIPS2020] SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks [Project]
• [NeurIPS2020] NVAE: A Deep Hierarchical Variational Autoencoder [pytorch]
• [NeurIPS2020] Implicit Graph Neural Networks [pytorch]
• [NeurIPS2020] The Autoencoding Variational Autoencoder [pytorch]
• [Arxiv] PointManifold: Using Manifold Learning for Point Cloud Classification
• [Arxiv] RelationNet++: Bridging Visual Representations for Object Detection via Transformer Decoder
• [Arxiv] Pre-Training by Completing Point Clouds [pytorch]
• [NeurIPS2020] Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloud
• [Arxiv] IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration [pytorch]
• [Arxiv] DV-ConvNet: Fully Convolutional Deep Learning on Point Clouds with Dynamic Voxelization and 3D Group Convolution
• [Arxiv] Spatial Transformer Point Convolution
• [Arxiv] Minimal Adversarial Examples for Deep Learning on 3D Point Clouds
• [BMVC2020] Black Magic in Deep Learning: How Human Skill Impacts Network Training
• [ECCV2020] PointMixup: Augmentation for Point Clouds [Code]
• [ECCV2020] DR-KFS: A Differentiable Visual Similarity Metric for 3D Shape Reconstruction
• [Arxiv] Unsupervised 3D Learning for Shape Analysis via Multiresolution Instance Discrimination
• [Arxiv] Global Context Aware Convolutions for 3D Point Cloud Understanding
• [ECCV2020] Shape Adaptor: A Learnable Resizing Module [pytorch]
• [ACMMM2020] Differentiable Manifold Reconstruction for Point Cloud Denoising [pytorch]
• [ECCV2020] Discrete Point Flow Networks for Efficient Point Cloud Generation
• [Siggraph2020] Neural Subdivision
• [Arxiv] PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
• [Arxiv] Accelerating 3D Deep Learning with PyTorch3D
• [Arxiv] Natural Graph Networks
• [ECCV2020] Progressive Point Cloud Deconvolution Generation Network [github]
• [Arxiv] Point Set Voting for Partial Point Cloud Analysis
• [Arxiv] PointMask: Towards Interpretable and Bias-Resilient Point Cloud Processing
• [Arxiv] Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernels
• [Arxiv] A Closer Look at Local Aggregation Operators in Point Cloud Analysis [github]
• [NeurIPS2020] Implicit Neural Representations with Periodic Activation Functions [pytorch] 🔥
• [Arxiv] Rethinking Sampling in 3D Point Cloud Generative Adversarial Networks
• [Arxiv] Local-Area-Learning Network: Meaningful Local Areas for Efficient Point Cloud Analysis
• [Arxiv] TearingNet: Point Cloud Autoencoder to Learn Topology-Friendly Representations
• [Arxiv] Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernels
• [Arxiv] Rethinking Sampling in 3D Point Cloud Generative Adversarial Networks
• [Arxiv] MeshWalker: Deep Mesh Understanding by Random Walks
• [Arxiv] MOPS-Net: A Matrix Optimization-driven Network for Task-Oriented 3D Point Cloud Downsampling
• [Arxiv] DPDist : Comparing Point Clouds Using Deep Point Cloud Distance
• [CVPR2020] PointASNL: Robust Point Clouds Processing using Nonlocal Neural Networks with Adaptive Sampling
• [AAAI2020] Shape-Oriented Convolution Neural Network for Point Cloud Analysis
• [Arxiv] Joint Supervised and Self-Supervised Learning for 3D Real-World Challenges
• [Arxiv] LIGHTCONVPOINT: CONVOLUTION FOR POINTS [pytorch]
• [Arxiv] Variational Auto-Decoder [pytorch]
• [Arxiv] Generative PointNet: Energy-Based Learning on Unordered Point Sets for 3D Generation, Reconstruction and Classification
• [CVPR2020] DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes [pytorch]
• [CVPR2020] RPM-Net: Robust Point Matching using Learned Features [github]
• [CVPR2020] Global-Local Bidirectional Reasoning for Unsupervised Representation Learning of 3D Point Clouds
• [CVPR2020] PointGMM: a Neural GMM Network for Point Clouds
• [Arxiv] Dynamic ReLU
• [CVPR2020] SampleNet: Differentiable Point Cloud Sampling [pytorch]
• [Arxiv] Defense-PointNet: Protecting PointNet Against Adversarial Attacks
• [CVPR2020] FPConv: Learning Local Flattening for Point Convolution [pytorch]
• [SIGGRAPH2019] MeshCNN: A Network with an Edge [pytorch] 🔥⭐
• [ICCV2019] Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaning [tensorflow]
• [ICCV2019] PU-GAN: a Point Cloud Upsampling Adversarial Network:fire:
• [CVPR2019] Relation-Shape Convolutional Neural Network for Point Cloud Analysis [pytorch] 🔥
• [CVPR2019] Patch-based Progressive 3D Point Set Upsampling [tensorflow] [pytorch] 🔥
• [TOG2019] Dynamic Graph CNN for Learning on Point Clouds [Project] 🔥 ⭐
• [ECCV2018] EC-Net: an Edge-aware Point set Consolidation Network [project page]
• [CVPR2018] PU-Net: Point Cloud Upsampling Network ⭐🔥
• [Arxiv] PointAugment: an Auto-Augmentation Framework for Point Cloud Classification
• [ICLR2017] DEEP LEARNING WITH SETS AND POINT CLOUDS
• [NeurIPS2017] Deep Sets
• [Siggraph2006] Designing with Distance Fields

• [ICML2021] Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifold [Project]
• [ICRA2021] An Adaptive Framework For Learning Unsupervised Depth Completion [github] [github]
• [ICRA2021] TSDF++: A Multi-Object Formulation for Dynamic Object Tracking and Reconstruction [github]
• [Siggraph2021] Orienting Point Clouds with Dipole Propagation
• [CVPR2021] The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth
• [Arxiv] Fully Convolutional Line Parsing [pytorch]
• [CVPR2021] Depth Completion using Plane-Residual Representation
• [Arxiv] Domain Adaptive Monocular Depth Estimation With Semantic Information
• [CVPR2021] Depth Completion with Twin Surface Extrapolation at Occlusion Boundaries [github]
• [Arxiv] Local Metrics for Multi-Object Tracking
• [Arxiv] Full Surround Monodepth from Multiple Cameras
• [CVPR2021] RGB-D Local Implicit Function for Depth Completion of Transparent Objects [Project]
• [CVPR2021] Learning Camera Localization via Dense Scene Matching [pytorch]
• [Arxiv] LSG-CPD: Coherent Point Drift with Local Surface Geometry for Point Cloud Registration
• [ICRA2021] PlaneSegNet: Fast and Robust Plane Estimation Using a Single-stage Instance Segmentation CNN
• [Arxiv] Learning Fine-Grained Segmentation of 3D Shapes without Part Labels
• [CVPR2021] Skeleton Merger: an Unsupervised Aligned Keypoint Detector
• [CVPR2021] Beyond Image to Depth: Improving Depth Prediction using Echoes
• [CVPR2021] FS-Net: Fast Shape-based Network for Category-Level 6D Object Pose Estimation with Decoupled Rotation Mechanism [Project]
• [CVPR2021] Self-supervised Geometric Perception
• [Arxiv] StablePose: Learning 6D Object Poses from Geometrically Stable Patches
• [Arxiv] A Parameterised Quantum Circuit Approach to Point Set Matching
• [Arxiv] Adjoint Rigid Transform Network: Self-supervised Alignment of 3D Shapes
• [Arxiv] Video Transformer Network
• [ICLR2021] NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimation [pytorch]
• [Arxiv] NBDT: NEURAL-BACKED DECISION TREE [pytorch]
• [Arxiv] AdaBins: Depth Estimation using Adaptive Bins [pytorch]
• [Arxiv] Unsupervised Monocular Depth Reconstruction of Non-Rigid Scenes
• [Arxiv] CorrNet3D: Unsupervised End-to-end Learning of Dense Correspondence for 3D Point Clouds

• [NeurIPS2019] PRNet: Self-Supervised Learning for Partial-to-Partial Registration [pytorch]
• [Arxiv] iNeRF: Inverting Neural Radiance Fields for Pose Estimation [Project]
• [Arxiv] Boosting Monocular Depth Estimation with Lightweight 3D Point Fusion
• [Arxiv] 3D Registration for Self-Occluded Objects in Context
• [Arxiv] Continuous Surface Embeddings
• [Arxiv] SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration
• [Arxiv] MVTN: Multi-View Transformation Network for 3D Shape Recognition
• [Arxiv] PREDATOR: Registration of 3D Point Clouds with Low Overlap
• [Arxiv] Deep Magnification-Arbitrary Upsampling over 3D Point Clouds
• [Arxiv] Occlusion Guided Scene Flow Estimation on 3D Point Clouds
• [NeurIPS2020] An Analysis of SVD for Deep Rotation Estimation
• [EG2020W] SHREC 2020 track: 6D object pose estimation
• [ACCV2020] Best Buddies Registration for Point Clouds
• [3DV] A New Distributional Ranking Loss With Uncertainty: Illustrated in Relative Depth Estimation
• [BMVC2020] View-consistent 4D Light Field Depth Estimation
• [BMVC2020] Neighbourhood-Insensitive Point Cloud Normal Estimation Network [Project]
• [ECCV2020] DeepGMR: Learning Latent Gaussian Mixture Models for Registration [Project]
• [ECCV2020] Motion Capture from Internet Videos [Project]
• [ECCV2020] Depth Completion with RGB Prior
• [ECCV2020] 6D Camera Relocalization in Ambiguous Scenes via Continuous Multimodal Inference
• [Arxiv] Self-Supervised Learning of Point Clouds via Orientation Estimation
• [SIGGRAPH2020] SymmetryNet: Learning to Predict Reflectional and Rotational Symmetries of 3D Shapes from Single-View RGB-D Images [Project]
• [ECCV2020] Learning Stereo from Single Images [github]
• [Arxiv] Learning Long-term Visual Dynamics with Region Proposal Interaction Networks [Project]
• [ECCV2020] Beyond Controlled Environments: 3D Camera Re-Localization in Changing Indoor Scenes [Project]
• [ECCV2020] Unsupervised Shape and Pose Disentanglement for 3D Meshes
• [Arxiv] PVSNet: Pixelwise Visibility-Aware Multi-View Stereo Network
• [ECCV2020] P²Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation
• [CVPR2020] Learning multiview 3D point cloud registration [pytorch]
• [CVPR2020] Feature-metric Registration: A Fast Semi-supervised Approach for Robust Point Cloud Registration without Correspondences
• [Siggraph2020] Consistent Video Depth Estimation
• [Arxiv] Deep Feature-preserving Normal Estimation for Point Cloud Filtering
• [Arxiv] Pseudo RGB-D for Self-Improving Monocular SLAM and Depth Prediction
• [CVPR2020] Towards Better Generalization: Joint Depth-Pose Learning without PoseNet [pytorch]
• [Arxiv] Monocular Camera Localization in Prior LiDAR Maps with 2D-3D Line Correspondences
• [Arxiv] Adversarial Texture Optimization from RGB-D Scans
• [Arxiv] SAPIEN: A SimulAted Part-based Interactive ENvironment
• [CVPR2020] G2L-Net: Global to Local Network for Real-time 6D Pose Estimation with Embedding Vector Features
• [Arxiv] On Localizing a Camera from a Single Image
• [Arxiv] DeepFit: 3D Surface Fitting via Neural Network Weighted Least Squares
• [CVPR2020] KFNet: Learning Temporal Camera Relocalization using Kalman Filtering
• [Arxiv] Neural Contours: Learning to Draw Lines from 3D Shapes
• [Arxiv] 3dDepthNet: Point Cloud Guided Depth Completion Network for Sparse Depth and Single Color Image
• [Arxiv] Unsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Sets
• [CVPR2020] End-to-End Learning Local Multi-view Descriptors for 3D Point Clouds
• [Arxiv] PnP-Net: A hybrid Perspective-n-Point Network
• [CVPR2020] MobilePose: Real-Time Pose Estimation for Unseen Objects with Weak Shape Supervision
• [CVPR2020] D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry
• [ICIP2020] TRIANGLE-NET: TOWARDS ROBUSTNESS IN POINT CLOUD CLASSIFICATION
• [ICRA2020] Robust 6D Object Pose Estimation by Learning RGB-D Features
• [Arxiv] Predicting Sharp and Accurate Occlusion Boundaries in Monocular Depth Estimation Using Displacement Fields
• [Arxiv] Single Image Depth Estimation Trained via Depth from Defocus Cues [pytorch]
• [Arxiv] DepthTransfer: Depth Extraction from Video Using Non-parametric Sampling
• [Arxiv] Target-less registration of point clouds: A review
• [Arxiv] Quaternion Equivariant Capsule Networks for 3D point clouds
• [Arxiv] Category-Level Articulated Object Pose Estimation
• [Arxiv] A Quantum Computational Approach to Correspondence Problems on Point Sets
• [Arxiv] DeepSFM: Structure From Motion Via Deep Bundle Adjustment
• [Arxiv] P²GNet: Pose-Guided Point Cloud Generating Networks for 6-DoF Object Pose Estimation
• [ICCV2019] Learning Local RGB-to-CAD Correspondences for Object Pose Estimation
• [ICCV2019] Joint Embedding of 3D Scan and CAD Objects [dataset]
• [ICLR2019] BA-NET: DENSE BUNDLE ADJUSTMENT NETWORKS [tensorflow]
• [ICCV2019] GP²C: Geometric Projection Parameter Consensus for Joint 3D Pose and Focal Length Estimation in the Wild
• [ICCV2019] Closed-Form Optimal Two-View Triangulation Based on Angular Errors
• [ICCV2019] Polarimetric Relative Pose Estimation
• [ICCV2019] End-to-End CAD Model Retrieval and 9DoF Alignment in 3D Scans
• [ICCV2019] Deep Non-Rigid Structure from Motion
• [CVPR2019] On the Continuity of Rotation Representations in Neural Networks [pytorch]
• [Arxiv] Deep Interpretable Non-Rigid Structure from Motion [tensorflow]
• [Arxiv] IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks [dataset]
• [CVPR2019] Scan2CAD: Learning CAD Model Alignment in RGB-D Scans [pytorch] 🔥
• [3DV2019] Location Field Descriptors: Single Image 3D Model Retrieval in the Wild
• [CVPR2016] Marr Revisited: 2D-3D Alignment via Surface Normal Prediction [caffe]

• [Arxiv] 3DB: A Framework for Debugging Computer Vision Models [github]
• [Arxiv] NViSII: A Scriptable Tool for Photorealistic Image Generation [github]
• [Dataset] Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling
• [Survey] 3D Semantic Scene Completion: a Survey
• [Survey] Deep Learning based 3D Segmentation: A Survey
• [Survey] A comprehensive survey on point cloud registration
• [Survey] Domain Generalization: A Survey
• [Dataset] SUM: A Benchmark Dataset of Semantic Urban Meshes
• [Survey] Attention Models for Point Clouds in Deep Learning: A Survey
• [Benchmark] H3D: Benchmark on Semantic Segmentation of High-Resolution 3D Point Clouds and textured Meshes from UAV LiDAR and Multi-View-Stereo [Project]
• [Survey] Dynamic Neural Networks: A Survey
• [Survey] Online Continual Learning in Image Classification: An Empirical Survey
• [Survey] Deep Learning for Visual Tracking: A Comprehensive Survey
• [Survey] Occlusion Handling in Generic Object Detection: A Review
• [Survey] Curriculum Learning: A Survey
• [Github] Awesome Neural Radiance Fields
• [Survey] Neural Volume Rendering: NeRF And Beyond
• [Survey] Transformers in Vision: A Survey
• [Survey] Efficient Transformers: A Survey
• [Survey] Semantics for Robotic Mapping, Perception and Interaction: A Survey
• [Survey] Generative Adversarial Networks in Computer Vision: A Survey and Taxonomy

• [Dataset] Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations [Github]
• [Survey] Skeleton-based Approaches based on Machine Vision: A Survey
• [Survey] Deep Learning-Based Human Pose Estimation: A Survey [Github]
• [Dataset] Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding [Github]
• [Survey] A Review and Comparative Study on Probabilistic Object Detection in Autonomous Driving [Github]
• [Dataset] RELLIS-3D Dataset: Data, Benchmarks and Analysis [Github]
• [Arxiv] Motion Prediction on Self-driving Cars: A Review
• [Github] TESSE: Unity-based simulator to enable research in perception, mapping, learning, and robotics
• [Survey] A Survey on Visual Transformer
• [Survey] A Survey on Contrastive Self-supervised Learning
• [Survey] A Survey of Surface Reconstruction from Point Clouds
• [Dataset] Torch-Points3D: A Modular Multi-Task Framework for Reproducible Deep Learning on 3D Point Clouds [Project]
• [Thesis] Learning to Reconstruct and Segment 3D Objects
• [Survey] An Overview Of 3D Object Detection
• [Survey] A Brief Review of Domain Adaptation
• [Dataset] Announcing the Objectron Dataset
• [Tutorial] Video Action Understanding: A Tutorial
• [Arxiv] Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Reconstruction [Page]
• [Survey] Multi-Task Learning with Deep Neural Networks: A Survey
• [Survey] Deep Learning for 3D Point Cloud Understanding: A Survey
• [Thesis] COMPUTATIONAL ANALYSIS OF DEFORMABLE MANIFOLDS: FROM GEOMETRIC MODELING TO DEEP LEARNING
• [Arxiv] F*: An Interpretable Transformation of the F-measure
• [Dataset] Gibson Database of 3D Spaces
• [BMVC2020] Black Magic in Deep Learning: How Human Skill Impacts Network Training
• [Arxiv] PyTorch Metric Learning
• [Arxiv] RGB-D Salient Object Detection: A Survey [Project]
• [Arxiv] AiRound and CV-BrCT: Novel Multi-View Datasets for Scene Classification [Project]
• [CVPR2020] OASIS: A Large-Scale Dataset for Single Image 3D in the Wild [Project]
• [Arxiv] 3D-FUTURE: 3D FUrniture shape with TextURE
• [Arxiv] 3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics [Project][Link]
• [Arxiv] Differentiable Rendering: A Survey
• [Arxiv] Visual Relationship Detection using Scene Graphs: A Survey
• [Arxiv] Polarization Human Shape and Pose Dataset
• [Arxiv] IDDA: a large-scale multi-domain dataset for autonomous driving [Project page]
• [CVPR2020] RoboTHOR: An Open Simulation-to-Real Embodied AI Platform [Project page]
• [EG2020] State of the Art on Neural Rendering
• [IJCAI-PRICAI2020] 3D-FUTURE: 3D FUrniture shape with TextURE
• [Arxiv] Toronto-3D: A Large-scale Mobile LiDAR Dataset for Semantic Segmentation of Urban Roadways
• [Arxiv] KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations
• [Arxiv] A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
• [Arxiv] From Seeing to Moving: A Survey on Learning for Visual Indoor Navigation (VIN)
• [Arxiv] DIODE: A Dense Indoor and Outdoor DEpth Dataset [dataset]
• [Github] Various GANs with Pytorch.
• [Arxiv] SemanticPOSS: A Point Cloud Dataset with Large Quantity of Dynamic Instances [dataset]
• [CVM] A Survey on Deep Geometry Learning: From a Representation Perspective
• [Arxiv] A survey on Semi-, Self- and Unsupervised Techniques in Image Classification
• [Arxiv] fastai: A Layered API for Deep Learning
• [Arxiv] AU-AIR: A Multi-modal Unmanned Aerial Vehicle Dataset for Low Altitude Traffic Surveillance [dataset]
• [Arxiv] VIRTUAL KITTI 2 [dataset]
• [Arxiv] Tutorial on Variational Autoencoders
• [Arxiv] Review: deep learning on 3D point clouds
• [Arxiv] Image Segmentation Using Deep Learning: A Survey
• [CVPR2018] Pixels, Voxels, and Views: A Study of Shape Representations for Single View 3D Object Shape Prediction
• [Arxiv] Evolution of Image Segmentation using Deep Convolutional Neural Network: A Survey
• [Arxiv] MCMLSD: A Probabilistic Algorithm and Evaluation Framework for Line Segment Detection
• [Arxiv] Deep Learning for 3D Point Clouds: A Survey
• [Arxiv] A Survey on Deep Learning-based Architectures for Semantic Segmentation on 2D images
• [Arxiv] A Survey on Deep Learning Architectures for Image-based Depth Reconstruction
• [Arxiv] secml: A Python Library for Secure and Explainable Machine Learning
• [Arxiv] Bundle Adjustment Revisited
• [ICCV2019] Deep CG2Real: Synthetic-to-Real Translation via Image Disentanglement
• [Arxiv] SIFT Meets CNN: A Decade Survey of Instance Retrieval
• [ICCV2019] Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data [tensorflow]
• [Arxiv] BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks [dataset]
• [Arxiv] Imbalance Problems in Object Detection: A Review [repository]
• [IJCV] Deep Learning for Generic Object Detection: A Survey
• [Arxiv] Differentiable Visual Computing (Ph.D thesis)
• [BMVC2018] InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset [dataset]
• [ICCV2017] The Mapillary Vistas Dataset for Semantic Understanding of Street Scenes [dataset] [script] ⭐
• [Arxiv] SynthCity: A large scale synthetic point cloud [dataset]
• [Github] Mesh Voxelization (SDFs or Occupancy grids)
• [Github] SDFGen (to generate grid-based signed distance field (level set))
• [Github] Blender renderer for python
• [Github] Blender renderer for python
• [Github] Volumetric TSDF Fusion of RGB-D Images in Python
• [Github] Volumetric TSDF Fusion of Multiple Depth Maps
• [Github] PyFusion
• [Github] PyRender
• [Github] PyMCubes
• [Github] Watertight and Simplified Meshes through TSDF Fusion (Python tool for obtaining watertight meshes using TSDF fusion.)
• [Github] Several tools about SDF functions.
• [Github] 3DMatch Toolbox
• [stackoverflow] Computing truncated signed distance function(TSDF) from a point cloud
• [Github] voxblox: A library for flexible voxel-based mapping, mainly focusing on truncated and Euclidean signed distance fields.
• [Github] Discregrid: A static C++ library for the generation of discrete functions on a box-shaped domain. This is especially suited for the generation of signed distance fields.
• [Github] awesome-voxel: Voxel resources for coders
• [Github] gvdb-voxels: Sparse volume compute and rendering on NVIDIA GPUs
• [Github] pyntcloud is a Python library for working with 3D point clouds.
• [Github] Open3D: A Modern Library for 3D Data Processing
• [Github] mesh_to_sdf: Calculate signed distance fields for arbitrary meshes
• [Github] Detecting & Penalizing Mesh Intersections
• [CVPR2021] Picasso: A CUDA-based Library for Deep Learning over 3D Meshes [Github]
• [Github] A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications
• [Arxiv] Shuffler: A Large Scale Data Management Tool for Machine Learning in Computer Vision