NeurIPS 2019 accepted papers on 3D vision
24 of the 1,429 papers accepted at NeurIPS 2019 (1.7%) are on 3D vision, compared with 1.5% at NeurIPS 2018. They fall into 4 topics.
See NeurIPS 2019 in the interactive map
Submitting to NeurIPS? 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
Face and shape · 8 papers
- Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer (254 citations)
- DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstruction (236 citations)
- Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations (88 citations)
- Learning to Infer Implicit Surfaces without 3D Supervision (86 citations)
- Multiview Aggregation for Learning Category-Specific Shape Reconstruction (27 citations)
- Learning elementary structures for 3D shape generation and matching (15 citations)
- A Condition Number for Joint Optimization of Cycle-Consistent Networks (12 citations)
- Fixing Implicit Derivatives: Trust-Region Based Learning of Continuous Energy Functions (2 citations)
3D generation · 6 papers
- CPM-Nets: Cross Partial Multi-View Networks (74 citations)
- Modeling Expectation Violation in Intuitive Physics with Coarse Probabilistic Object Representations (58 citations)
- PerspectiveNet: A Scene-consistent Image Generator for New View Synthesis in Real Indoor Environments (20 citations)
- Geometry-Aware Neural Rendering (11 citations)
- Neural Multisensory Scene Inference (2 citations)
- Incremental Scene Synthesis
Depth and stereo · 5 papers
- Invert to Learn to Invert (36 citations)
- Cascaded Dilated Dense Network with Two-step Data Consistency for MRI Reconstruction (33 citations)
- Deep RGB-D Canonical Correlation Analysis For Sparse Depth Completion (24 citations)
- Bat-G net: Bat-inspired High-Resolution 3D Image Reconstruction using Ultrasonic Echoes (6 citations)
- Region-specific Diffeomorphic Metric Mapping (4 citations)
Human pose estimation · 5 papers
- Sim2real transfer learning for 3D human pose estimation: motion to the rescue (68 citations)
- Domes to Drones: Self-Supervised Active Triangulation for 3D Human Pose Reconstruction (27 citations)
- Third-Person Visual Imitation Learning via Decoupled Hierarchical Controller (24 citations)
- Learning Temporal Pose Estimation from Sparsely-Labeled Videos (16 citations)
- Chirality Nets for Human Pose Regression (14 citations)
