Correspondence-Free SE(3) Point Cloud Registration in RKHS via Unsupervised Equivariant Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917736363327488 |
|---|---|
| author | Zhang, Ray Zhou, Zheming Sun, Min Ghasemalizadeh, Omid Kuo, Cheng-Hao Eustice, Ryan Ghaffari, Maani Sen, Arnie |
| author_facet | Zhang, Ray Zhou, Zheming Sun, Min Ghasemalizadeh, Omid Kuo, Cheng-Hao Eustice, Ryan Ghaffari, Maani Sen, Arnie |
| contents | This paper introduces a robust unsupervised SE(3) point cloud registration method that operates without requiring point correspondences. The method frames point clouds as functions in a reproducing kernel Hilbert space (RKHS), leveraging SE(3)-equivariant features for direct feature space registration. A novel RKHS distance metric is proposed, offering reliable performance amidst noise, outliers, and asymmetrical data. An unsupervised training approach is introduced to effectively handle limited ground truth data, facilitating adaptation to real datasets. The proposed method outperforms classical and supervised methods in terms of registration accuracy on both synthetic (ModelNet40) and real-world (ETH3D) noisy, outlier-rich datasets. To our best knowledge, this marks the first instance of successful real RGB-D odometry data registration using an equivariant method. The code is available at {https://sites.google.com/view/eccv24-equivalign} |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_20223 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Correspondence-Free SE(3) Point Cloud Registration in RKHS via Unsupervised Equivariant Learning Zhang, Ray Zhou, Zheming Sun, Min Ghasemalizadeh, Omid Kuo, Cheng-Hao Eustice, Ryan Ghaffari, Maani Sen, Arnie Computer Vision and Pattern Recognition Robotics This paper introduces a robust unsupervised SE(3) point cloud registration method that operates without requiring point correspondences. The method frames point clouds as functions in a reproducing kernel Hilbert space (RKHS), leveraging SE(3)-equivariant features for direct feature space registration. A novel RKHS distance metric is proposed, offering reliable performance amidst noise, outliers, and asymmetrical data. An unsupervised training approach is introduced to effectively handle limited ground truth data, facilitating adaptation to real datasets. The proposed method outperforms classical and supervised methods in terms of registration accuracy on both synthetic (ModelNet40) and real-world (ETH3D) noisy, outlier-rich datasets. To our best knowledge, this marks the first instance of successful real RGB-D odometry data registration using an equivariant method. The code is available at {https://sites.google.com/view/eccv24-equivalign} |
| title | Correspondence-Free SE(3) Point Cloud Registration in RKHS via Unsupervised Equivariant Learning |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2407.20223 |