NeurIPS 2020 accepted papers on Point clouds
18 of the 1,901 papers accepted at NeurIPS 2020 (0.9%) are on Point clouds, compared with 0.7% at NeurIPS 2019. They fall into 3 topics.
See NeurIPS 2020 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
Point cloud classification · 10 papers
- SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks (258 citations)
- Pushing the Limits of Narrow Precision Inferencing at Cloud Scale with Microsoft Floating Point (52 citations)
- Self-Supervised Few-Shot Learning on Point Clouds (49 citations)
- Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloud (46 citations)
- PIE-NET: Parametric Inference of Point Cloud Edges (43 citations)
- Exchangeable Neural ODE for Set Modeling (14 citations)
- Learning to Orient Surfaces by Self-supervised Spherical CNNs (9 citations)
- Correspondence learning via linearly-invariant embedding (4 citations)
- Equivariant Networks for Hierarchical Structures (3 citations)
- Group Contextual Encoding for 3D Point Clouds (3 citations)
Shape and surface completion · 6 papers
- Learning Deformable Tetrahedral Meshes for 3D Reconstruction (58 citations)
- SoftFlow: Probabilistic Framework for Normalizing Flow on Manifolds (51 citations)
- Skeleton-bridged Point Completion: From Global Inference to Local Adjustment (39 citations)
- CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations (36 citations)
- Neural Unsigned Distance Fields for Implicit Function Learning (31 citations)
- Learning Implicit Functions for Topology-Varying Dense 3D Shape Correspondence (4 citations)
