AAAI 2022 accepted papers on Point clouds
24 of the 1,319 papers accepted at AAAI 2022 (1.8%) are on Point clouds, compared with 1.2% at AAAI 2021. They fall into 4 topics.
See AAAI 2022 in the interactive map
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
- OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compression (196 citations)
- SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition (88 citations)
- SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-training for Spatial-Aware Visual Representations (53 citations)
- SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation (41 citations)
- Learning to Detect 3D Facial Landmarks via Heatmap Regression with Graph Convolutional Network (25 citations)
- Shape Prior Guided Attack: Sparser Perturbations on 3D Point Clouds (17 citations)
- Self-Supervised Robust Scene Flow Estimation via the Alignment of Probability Density Functions (12 citations)
- DuMLP-Pin: A Dual-MLP-Dot-Product Permutation-Invariant Network for Set Feature Extraction (7 citations)
- Modify Self-Attention via Skeleton Decomposition for Effective Point Cloud Transformer (7 citations)
- Graph-Based Point Tracker for 3D Object Tracking in Point Clouds (2 citations)
Segmentation and detection · 7 papers
- Behind the Curtain: Learning Occluded Shapes for 3D Object Detection (192 citations)
- SASA: Semantics-Augmented Set Abstraction for Point-Based 3D Object Detection (161 citations)
- Transfer Learning from Synthetic to Real LiDAR Point Cloud for Semantic Segmentation (117 citations)
- SVGA-Net: Sparse Voxel-Graph Attention Network for 3D Object Detection from Point Clouds (109 citations)
- Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspective (33 citations)
- JPV-Net: Joint Point-Voxel Representations for Accurate 3D Object Detection (11 citations)
- SCIR-Net: Structured Color Image Representation Based 3D Object Detection Network from Point Clouds (4 citations)
Registration and matching · 5 papers
- FINet: Dual Branches Feature Interaction for Partial-to-Partial Point Cloud Registration (77 citations)
- Reliable Inlier Evaluation for Unsupervised Point Cloud Registration (63 citations)
- DeTarNet: Decoupling Translation and Rotation by Siamese Network for Point Cloud Registration (32 citations)
- End-to-End Learning the Partial Permutation Matrix for Robust 3D Point Cloud Registration (32 citations)
- Deep Confidence Guided Distance for 3D Partial Shape Registration (5 citations)
