Few-Shot Point Cloud Semantic Segmentation via Contrastive Self-Supervision and Multi-Resolution Attention.
Jiahui WangHaiyue ZhuHaoren GuoAbdullah Al MamunCheng-Xiang WangTong Heng LeePublished in: ICRA (2023)
Keyphrases
- point cloud
- semantic segmentation
- multiresolution
- superpixels
- conditional random fields
- structure from motion
- weakly supervised
- scene classification
- object class
- object categories
- point sets
- object classes
- video data
- visual attention
- multiscale
- video sequences
- object recognition
- video frames
- visual features
- graphical models
- input image
- ground truth
- active learning
- feature selection
- sparse reconstruction