NeurIPS 2021 accepted papers on Point clouds
23 of the 2,508 papers accepted at NeurIPS 2021 (0.9%) are on Point clouds, compared with 0.9% at NeurIPS 2020. They fall into 4 topics.
See NeurIPS 2021 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 · 11 papers
- Three-dimensional spike localization and improved motion correction for Neuropixels recordings (40 citations)
- ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation Learning (39 citations)
- Canonical Capsules: Self-Supervised Capsules in Canonical Pose (35 citations)
- SE(3)-equivariant prediction of molecular wavefunctions and electronic densities (25 citations)
- Adversarially Robust 3D Point Cloud Recognition Using Self-Supervisions (18 citations)
- Knowledge-inspired 3D Scene Graph Prediction in Point Cloud (16 citations)
- Pooling by Sliced-Wasserstein Embedding (8 citations)
- Interpreting Representation Quality of DNNs for 3D Point Cloud Processing (7 citations)
- Particle Cloud Generation with Message Passing Generative Adversarial Networks (6 citations)
- Neural Scene Flow Prior
- Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting
Shape and surface completion · 5 papers
- Balanced Chamfer Distance as a Comprehensive Metric for Point Cloud Completion (29 citations)
- Learning 3D Dense Correspondence via Canonical Point Autoencoder (13 citations)
- Shape As Points: A Differentiable Poisson Solver (5 citations)
- Matrix factorisation and the interpretation of geodesic distance (4 citations)
- Differentiable Spline Approximations (1 citation)
Segmentation and detection · 4 papers
- Multimodal Virtual Point 3D Detection (125 citations)
- Learning Transferable Features for Point Cloud Detection via 3D Contrastive Co-training (19 citations)
- PolarStream: Streaming Object Detection and Segmentation with Polar Pillars (18 citations)
- 3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds
