CVPR 2019 accepted papers on 3D vision
209 of the 1,294 papers accepted at CVPR 2019 (16.2%) are on 3D vision, compared with 18.7% at CVPR 2018. They fall into 4 topics.
See CVPR 2019 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 · 86 papers
- Group-Wise Correlation Stereo Network (768 citations)
- Recurrent MVSNet for High-Resolution Multi-View Stereo Depth Inference (682 citations)
- Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation (674 citations)
- DeepView: View Synthesis With Learned Gradient Descent (434 citations)
- DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene From Sparse LiDAR Data and Single Color Image (420 citations)
- Depth-Attentional Features for Single-Image Rain Removal (410 citations)
- End-To-End Interpretable Neural Motion Planner (408 citations)
- BAD SLAM: Bundle Adjusted Direct RGB-D SLAM (391 citations)
- Pushing the Boundaries of View Extrapolation With Multiplane Images (348 citations)
- L3-Net: Towards Learning Based LiDAR Localization for Autonomous Driving (320 citations)
- Towards Scene Understanding: Unsupervised Monocular Depth Estimation With Semantic-Aware Representation (275 citations)
- Multi-Scale Geometric Consistency Guided Multi-View Stereo (263 citations)
and 74 more in the interactive map.
Human pose estimation · 53 papers
- Deep High-Resolution Representation Learning for Human Pose Estimation (5,835 citations)
- Expressive Body Capture: 3D Hands, Face, and Body From a Single Image (1,796 citations)
- DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion (1,158 citations)
- PVNet: Pixel-Wise Voting Network for 6DoF Pose Estimation (1,079 citations)
- CrowdPose: Efficient Crowded Scenes Pose Estimation and a New Benchmark (623 citations)
- Convolutional Mesh Regression for Single-Image Human Shape Reconstruction (584 citations)
- PifPaf: Composite Fields for Human Pose Estimation (557 citations)
- Understanding the Limitations of CNN-Based Absolute Camera Pose Regression (408 citations)
- FSA-Net: Learning Fine-Grained Structure Aggregation for Head Pose Estimation From a Single Image (351 citations)
- Monocular Total Capture: Posing Face, Body, and Hands in the Wild (350 citations)
- Learning Individual Styles of Conversational Gesture (346 citations)
- Segmentation-Driven 6D Object Pose Estimation (336 citations)
and 41 more in the interactive map.
Face and shape · 47 papers
- DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation (3,528 citations)
- Occupancy Networks: Learning 3D Reconstruction in Function Space (2,830 citations)
- Learning Implicit Fields for Generative Shape Modeling (1,503 citations)
- ABC: A Big CAD Model Dataset for Geometric Deep Learning (533 citations)
- Capture, Learning, and Synthesis of 3D Speaking Styles (366 citations)
- Learning to Reconstruct People in Clothing From a Single RGB Camera (351 citations)
- Learning to Regress 3D Face Shape and Expression From an Image Without 3D Supervision (346 citations)
- GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction (332 citations)
- Gait Recognition via Disentangled Representation Learning (292 citations)
- X2CT-GAN: Reconstructing CT From Biplanar X-Rays With Generative Adversarial Networks (253 citations)
- Scan2CAD: Learning CAD Model Alignment in RGB-D Scans (245 citations)
- SiCloPe: Silhouette-Based Clothed People (214 citations)
and 35 more in the interactive map.
3D generation · 23 papers
- Argoverse: 3D Tracking and Forecasting With Rich Maps (1,487 citations)
- DeepVoxels: Learning Persistent 3D Feature Embeddings (601 citations)
- Learning Joint Reconstruction of Hands and Manipulated Objects (527 citations)
- What Do Single-View 3D Reconstruction Networks Learn? (455 citations)
- Dissecting Person Re-Identification From the Viewpoint of Viewpoint (279 citations)
- Neural Rerendering in the Wild (204 citations)
- ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaging (202 citations)
- ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving (195 citations)
- HorizonNet: Learning Room Layout With 1D Representation and Pano Stretch Data Augmentation (190 citations)
- Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models (155 citations)
- DuLa-Net: A Dual-Projection Network for Estimating Room Layouts From a Single RGB Panorama (151 citations)
- Towards Natural and Accurate Future Motion Prediction of Humans and Animals (149 citations)
and 11 more in the interactive map.
