1. Multi-Features Guidance Network for partial-to-partial point cloud registration
- Author
-
Wang Bingwen, Kang Wen, Yan Zhiqiang, Liu Xiang, Hongyuan Wang, and Qianhao Ning
- Subjects
FOS: Computer and information sciences ,Matching (graph theory) ,Computer science ,business.industry ,Computation ,Computer Vision and Pattern Recognition (cs.CV) ,Feature extraction ,Computer Science - Computer Vision and Pattern Recognition ,Point cloud ,Pattern recognition ,Rotation matrix ,Translation (geometry) ,Artificial Intelligence ,Spatial reference system ,Singular value decomposition ,Artificial intelligence ,business ,Software - Abstract
To eliminate the problems of large dimensional differences, big semantic gap, and mutual interference caused by hybrid features, in this paper, we propose a novel Multi-Features Guidance Network for partial-to-partial point cloud registration(MFG). The proposed network mainly includes four parts: keypoints' feature extraction, correspondences searching, correspondences credibility computation, and SVD, among which correspondences searching and correspondence credibility computation are the cores of the network. Unlike the previous work, we utilize the shape features and the spatial coordinates to guide correspondences search independently and fusing the matching results to obtain the final matching matrix. In the correspondences credibility computation module, based on the conflicted relationship between the features matching matrix and the coordinates matching matrix, we score the reliability for each correspondence, which can reduce the impact of mismatched or non-matched points. Experimental results show that our network outperforms the current state-of-the-art while maintaining computational efficiency., Comment: preprint version, the final version is accepted by Neural Computing and Applications and is available online at https://doi.org/10.1007/s00521-021-06464-y
- Published
- 2020
- Full Text
- View/download PDF