CVPR 2020 accepted papers on Point clouds
70 of the 1,467 papers accepted at CVPR 2020 (4.8%) are on Point clouds, compared with 4.1% at CVPR 2019. They fall into 4 topics.
See CVPR 2020 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
Point cloud classification · 25 papers
- PointASNL: Robust Point Clouds Processing Using Nonlocal Neural Networks With Adaptive Sampling (677 citations)
- Convolution in the Cloud: Learning Deformable Kernels in 3D Graph Convolution Networks for Point Cloud Analysis (264 citations)
- Grid-GCN for Fast and Scalable Point Cloud Learning (257 citations)
- LiDARsim: Realistic LiDAR Simulation by Leveraging the Real World (239 citations)
- OctSqueeze: Octree-Structured Entropy Model for LiDAR Compression (211 citations)
- SampleNet: Differentiable Point Cloud Sampling (204 citations)
- PointAugment: An Auto-Augmentation Framework for Point Cloud Classification (191 citations)
- ACNe: Attentive Context Normalization for Robust Permutation-Equivariant Learning (178 citations)
- FPConv: Learning Local Flattening for Point Convolution (176 citations)
- P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds (173 citations)
- Adaptive Hierarchical Down-Sampling for Point Cloud Classification (155 citations)
- An Efficient PointLSTM for Point Clouds Based Gesture Recognition (138 citations)
and 13 more in the interactive map.
Segmentation and detection · 21 papers
- PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection (2,171 citations)
- RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds (2,138 citations)
- PointPainting: Sequential Fusion for 3D Object Detection (1,229 citations)
- 3DSSD: Point-Based 3D Single Stage Object Detector (1,152 citations)
- Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloud (969 citations)
- Structure Aware Single-Stage 3D Object Detection From Point Cloud (676 citations)
- PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation (597 citations)
- PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation (477 citations)
- ImVoteNet: Boosting 3D Object Detection in Point Clouds With Image Votes (314 citations)
- Learning Depth-Guided Convolutions for Monocular 3D Object Detection (275 citations)
- 3D-MPA: Multi-Proposal Aggregation for 3D Semantic Instance Segmentation (237 citations)
- End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection (205 citations)
and 9 more in the interactive map.
Shape and surface completion · 16 papers
- PF-Net: Point Fractal Network for 3D Point Cloud Completion (510 citations)
- SAL: Sign Agnostic Learning of Shapes From Raw Data (453 citations)
- Point Cloud Completion by Skip-Attention Network With Hierarchical Folding (288 citations)
- Cascaded Refinement Network for Point Cloud Completion (277 citations)
- Deep Iterative Surface Normal Estimation (85 citations)
- SSRNet: Scalable 3D Surface Reconstruction Network (66 citations)
- PointGMM: A Neural GMM Network for Point Clouds (65 citations)
- Shape Reconstruction by Learning Differentiable Surface Representations (52 citations)
- Unsupervised Learning of Intrinsic Structural Representation Points (49 citations)
- PFCNN: Convolutional Neural Networks on 3D Surfaces Using Parallel Frames (45 citations)
- Geometry and Learning Co-Supported Normal Estimation for Unstructured Point Cloud (41 citations)
- AdaCoSeg: Adaptive Shape Co-Segmentation With Group Consistency Loss (37 citations)
and 4 more in the interactive map.
Registration and matching · 8 papers
- RPM-Net: Robust Point Matching Using Learned Features (623 citations)
- D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features (519 citations)
- Feature-Metric Registration: A Fast Semi-Supervised Approach for Robust Point Cloud Registration Without Correspondences (325 citations)
- 3DRegNet: A Deep Neural Network for 3D Point Registration (276 citations)
- Learning Multiview 3D Point Cloud Registration (200 citations)
- Global Optimality for Point Set Registration Using Semidefinite Programming (37 citations)
- A Quantum Computational Approach to Correspondence Problems on Point Sets (28 citations)
- Minimal Solvers for 3D Scan Alignment With Pairs of Intersecting Lines (10 citations)
