Coarse-to-Fine Point Cloud Registration with SE(3)-Equivariant Representations.
Cheng-Wei LinTung-I ChenHsin-Ying LeeWen-Chin ChenWinston H. HsuPublished in: CoRR (2022)
Keyphrases
- point cloud
- coarse to fine
- multiscale
- image registration
- multiresolution
- structure from motion
- surface reconstruction
- hierarchical segmentation
- object detection
- point sets
- laser scanner
- point cloud data
- iterative closest point
- active shape model
- matching scheme
- dynamic programming
- stereo camera
- optical flow estimation
- real world objects
- icp algorithm
- computer vision
- reinforcement learning
- rigid registration
- knn
- pairwise