We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
NrtNet: An Unsupervised Method for 3D Non-Rigid Point Cloud Registration Based on Transformer.
- Authors
Hu, Xiaobo; Zhang, Dejun; Chen, Jinzhi; Wu, Yiqi; Chen, Yilin
- Abstract
Self-attention networks have revolutionized the field of natural language processing and have also made impressive progress in image analysis tasks. Corrnet3D proposes the idea of first obtaining the point cloud correspondence in point cloud registration. Inspired by these successes, we propose an unsupervised network for non-rigid point cloud registration, namely NrtNet, which is the first network using a transformer for unsupervised large deformation non-rigid point cloud registration. Specifically, NrtNet consists of a feature extraction module, a correspondence matrix generation module, and a reconstruction module. Feeding a pair of point clouds, our model first learns the point-by-point features and feeds them to the transformer-based correspondence matrix generation module, which utilizes the transformer to learn the correspondence probability between pairs of point sets, and then the correspondence probability matrix conducts normalization to obtain the correct point set corresponding matrix. We then permute the point clouds and learn the relative drift of the point pairs to reconstruct the point clouds for registration. Extensive experiments on synthetic and real datasets of non-rigid 3D shapes show that NrtNet outperforms state-of-the-art methods, including methods that use grids as input and methods that directly compute point drift.
- Subjects
POINT cloud; POINT set theory; NATURAL language processing; BINARY codes; FEATURE extraction; TASK analysis; IMAGE analysis
- Publication
Sensors (14248220), 2022, Vol 22, Issue 14, pN.PAG
- ISSN
1424-8220
- Publication type
Article
- DOI
10.3390/s22145128