NeurIPS 2018 accepted papers on 3D vision
15 of the 1,008 papers accepted at NeurIPS 2018 (1.5%) are on 3D vision, compared with 0.7% at NeurIPS 2017. They fall into 4 topics.
See NeurIPS 2018 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 · 7 papers
- 3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data (248 citations)
- Visual Object Networks: Image Generation with Disentangled 3D Representations (146 citations)
- Learning to Reconstruct Shapes from Unseen Classes (105 citations)
- RenderNet: A deep convolutional network for differentiable rendering from 3D shapes (63 citations)
- Learning a High Fidelity Pose Invariant Model for High-resolution Face Frontalization (55 citations)
- 3D-Aware Scene Manipulation via Inverse Graphics (44 citations)
- Unsupervised Depth Estimation, 3D Face Rotation and Replacement (21 citations)
3D generation · 5 papers
- See and Think: Disentangling Semantic Scene Completion (81 citations)
- Learning to Exploit Stability for 3D Scene Parsing (31 citations)
- Geometry-Aware Recurrent Neural Networks for Active Visual Recognition (16 citations)
- Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation (9 citations)
- Cooperative Holistic Scene Understanding: Unifying 3D Object, Layout, and Camera Pose Estimation (7 citations)
Human pose estimation · 2 papers
Depth and stereo · 1 paper
- LF-Net: Learning Local Features from Images (348 citations)
