CVPR 2020 accepted papers on 3D vision
264 of the 1,467 papers accepted at CVPR 2020 (18.0%) are on 3D vision, compared with 16.2% at CVPR 2019. They fall into 5 topics.
See CVPR 2020 in the interactive map
Submitting to CVPR? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Depth and stereo · 83 papers
- SuperGlue: Learning Feature Matching With Graph Neural Networks (2,845 citations)
- Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching (876 citations)
- 3D Packing for Self-Supervised Monocular Depth Estimation (749 citations)
- BlendedMVS: A Large-Scale Dataset for Generalized Multi-View Stereo Networks (481 citations)
- D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry (431 citations)
- Deep Stereo Using Adaptive Thin Volume Representation With Uncertainty Awareness (376 citations)
- ASLFeat: Learning Local Features of Accurate Shape and Localization (359 citations)
- Cost Volume Pyramid Based Depth Inference for Multi-View Stereo (354 citations)
- 3D Photography Using Context-Aware Layered Depth Inpainting (287 citations)
- Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline (285 citations)
- Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement (250 citations)
- Where Am I Looking At? Joint Location and Orientation Estimation by Cross-View Matching (215 citations)
and 71 more in the interactive map.
Human pose estimation · 82 papers
- VIBE: Video Inference for Human Body Pose and Shape Estimation (1,076 citations)
- HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation (954 citations)
- GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping (667 citations)
- PVN3D: A Deep Point-Wise 3D Keypoints Voting Network for 6DoF Pose Estimation (611 citations)
- Distribution-Aware Coordinate Representation for Human Pose Estimation (561 citations)
- Deep Global Registration (559 citations)
- HOnnotate: A Method for 3D Annotation of Hand and Object Poses (427 citations)
- GHUM & GHUML: Generative 3D Human Shape and Articulated Pose Models (351 citations)
- HybridPose: 6D Object Pose Estimation Under Hybrid Representations (315 citations)
- The Devil Is in the Details: Delving Into Unbiased Data Processing for Human Pose Estimation (281 citations)
- Attention Mechanism Exploits Temporal Contexts: Real-Time 3D Human Pose Reconstruction (275 citations)
- EPOS: Estimating 6D Pose of Objects With Symmetries (247 citations)
and 70 more in the interactive map.
Face and shape · 68 papers
- RetinaFace: Single-Shot Multi-Level Face Localisation in the Wild (1,623 citations)
- Differentiable Volumetric Rendering: Learning Implicit 3D Representations Without 3D Supervision (880 citations)
- PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization (800 citations)
- Local Implicit Grid Representations for 3D Scenes (550 citations)
- Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion (532 citations)
- Local Deep Implicit Functions for 3D Shape (397 citations)
- StyleRig: Rigging StyleGAN for 3D Control Over Portrait Images (374 citations)
- Learning to Dress 3D People in Generative Clothing (373 citations)
- ARCH: Animatable Reconstruction of Clothed Humans (358 citations)
- View-GCN: View-Based Graph Convolutional Network for 3D Shape Analysis (337 citations)
- FaceScape: A Large-Scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction (319 citations)
- TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style (307 citations)
and 56 more in the interactive map.
3D generation · 30 papers
- Scalability in Perception for Autonomous Driving: Waymo Open Dataset (3,252 citations)
- SynSin: End-to-End View Synthesis From a Single Image (434 citations)
- Single-View View Synthesis With Multiplane Images (315 citations)
- OccuSeg: Occupancy-Aware 3D Instance Segmentation (260 citations)
- Learning 3D Semantic Scene Graphs From 3D Indoor Reconstructions (245 citations)
- Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes From a Single Image (240 citations)
- Mapillary Street-Level Sequences: A Dataset for Lifelong Place Recognition (227 citations)
- The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction (182 citations)
- Context-Aware Human Motion Prediction (158 citations)
- Anisotropic Convolutional Networks for 3D Semantic Scene Completion (144 citations)
- 3D Sketch-Aware Semantic Scene Completion via Semi-Supervised Structure Prior (136 citations)
- ARShadowGAN: Shadow Generative Adversarial Network for Augmented Reality in Single Light Scenes (123 citations)
and 18 more in the interactive map.
NeRF and radiance fields · 1 paper
- A Neural Rendering Framework for Free-Viewpoint Relighting (47 citations)
