CVPR 2016 accepted papers on 3D vision
126 of the 643 papers accepted at CVPR 2016 (19.6%) are on 3D vision. They fall into 4 topics.
See CVPR 2016 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 · 66 papers
- Structure-From-Motion Revisited (6,291 citations)
- A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation (2,292 citations)
- Learning Dense Correspondence via 3D-Guided Cycle Consistency (362 citations)
- Simultaneous Optical Flow and Intensity Estimation From an Event Camera (306 citations)
- Pairwise Decomposition of Image Sequences for Active Multi-View Recognition (247 citations)
- Dense Monocular Depth Estimation in Complex Dynamic Scenes (191 citations)
- A Benchmark Dataset and Evaluation for Non-Lambertian and Uncalibrated Photometric Stereo (161 citations)
- Convolutional Networks for Shape From Light Field (118 citations)
- HyperDepth: Learning Depth From Structured Light Without Matching (108 citations)
- Egocentric Future Localization (106 citations)
- Robust Light Field Depth Estimation for Noisy Scene With Occlusion (103 citations)
- High-Quality Depth From Uncalibrated Small Motion Clip (99 citations)
and 54 more in the interactive map.
Face and shape · 26 papers
- Face Alignment Across Large Poses: A 3D Solution (1,211 citations)
- A 3D Morphable Model Learnt From 10,000 Faces (376 citations)
- Large-Pose Face Alignment via CNN-Based Dense 3D Model Fitting (302 citations)
- Pose-Aware Face Recognition in the Wild (260 citations)
- GIFT: A Real-Time and Scalable 3D Shape Search Engine (256 citations)
- Marr Revisited: 2D-3D Alignment via Surface Normal Prediction (236 citations)
- Structured Prediction of Unobserved Voxels From a Single Depth Image (199 citations)
- Unconstrained Face Alignment via Cascaded Compositional Learning (192 citations)
- Dense Human Body Correspondences Using Convolutional Networks (187 citations)
- Adaptive 3D Face Reconstruction From Unconstrained Photo Collections (152 citations)
- A Field Model for Repairing 3D Shapes (117 citations)
- Large-Scale Semantic 3D Reconstruction: An Adaptive Multi-Resolution Model for Multi-Class Volumetric Labeling (91 citations)
and 14 more in the interactive map.
Human pose estimation · 22 papers
- Convolutional Pose Machines (2,831 citations)
- DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation (1,103 citations)
- Human Pose Estimation With Iterative Error Feedback (856 citations)
- Uncertainty-Driven 6D Pose Estimation of Objects and Scenes From a Single RGB Image (558 citations)
- Sparseness Meets Deepness: 3D Human Pose Estimation From Monocular Video (440 citations)
- End-To-End Learning of Deformable Mixture of Parts and Deep Convolutional Neural Networks for Human Pose Estimation (288 citations)
- Structured Feature Learning for Pose Estimation (288 citations)
- Robust 3D Hand Pose Estimation in Single Depth Images: From Single-View CNN to Multi-View CNNs (272 citations)
- Direct Prediction of 3D Body Poses From Motion Compensated Sequences (244 citations)
- Recovering 6D Object Pose and Predicting Next-Best-View in the Crowd (240 citations)
- Rolling Rotations for Recognizing Human Actions From 3D Skeletal Data (224 citations)
- A Dual-Source Approach for 3D Pose Estimation From a Single Image (211 citations)
and 10 more in the interactive map.
3D generation · 12 papers
- Volumetric and Multi-View CNNs for Object Classification on 3D Data (1,610 citations)
- Understanding Real World Indoor Scenes With Synthetic Data (243 citations)
- Multi-View People Tracking via Hierarchical Trajectory Composition (175 citations)
- BoxCars: 3D Boxes as CNN Input for Improved Fine-Grained Vehicle Recognition (172 citations)
- DeLay: Robust Spatial Layout Estimation for Cluttered Indoor Scenes (155 citations)
- WarpNet: Weakly Supervised Matching for Single-View Reconstruction (137 citations)
- Newtonian Scene Understanding: Unfolding the Dynamics of Objects in Static Images (124 citations)
- DeepStereo: Learning to Predict New Views From the World's Imagery (83 citations)
- Inferring Forces and Learning Human Utilities From Videos (83 citations)
- Learning Action Maps of Large Environments via First-Person Vision (35 citations)
- Volumetric 3D Tracking by Detection (32 citations)
- Consistency of Silhouettes and Their Duals (3 citations)
