GS-Matching: Reconsidering Feature Matching task in Point Cloud Registration
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912147101974528 |
|---|---|
| author | Zhang, Yaojie Huang, Tianlun Wang, Weijun Feng, Wei |
| author_facet | Zhang, Yaojie Huang, Tianlun Wang, Weijun Feng, Wei |
| contents | Traditional point cloud registration (PCR) methods for feature matching often employ the nearest neighbor policy. This leads to many-to-one matches and numerous potential inliers without any corresponding point. Recently, some approaches have framed the feature matching task as an assignment problem to achieve optimal one-to-one matches. We argue that the transition to the Assignment problem is not reliable for general correspondence-based PCR. In this paper, we propose a heuristics stable matching policy called GS-matching, inspired by the Gale-Shapley algorithm. Compared to the other matching policies, our method can perform efficiently and find more non-repetitive inliers under low overlapping conditions. Furthermore, we employ the probability theory to analyze the feature matching task, providing new insights into this research problem. Extensive experiments validate the effectiveness of our matching policy, achieving better registration recall on multiple datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_04855 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GS-Matching: Reconsidering Feature Matching task in Point Cloud Registration Zhang, Yaojie Huang, Tianlun Wang, Weijun Feng, Wei Computer Vision and Pattern Recognition Traditional point cloud registration (PCR) methods for feature matching often employ the nearest neighbor policy. This leads to many-to-one matches and numerous potential inliers without any corresponding point. Recently, some approaches have framed the feature matching task as an assignment problem to achieve optimal one-to-one matches. We argue that the transition to the Assignment problem is not reliable for general correspondence-based PCR. In this paper, we propose a heuristics stable matching policy called GS-matching, inspired by the Gale-Shapley algorithm. Compared to the other matching policies, our method can perform efficiently and find more non-repetitive inliers under low overlapping conditions. Furthermore, we employ the probability theory to analyze the feature matching task, providing new insights into this research problem. Extensive experiments validate the effectiveness of our matching policy, achieving better registration recall on multiple datasets. |
| title | GS-Matching: Reconsidering Feature Matching task in Point Cloud Registration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.04855 |