Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.18922 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911020159598592 |
|---|---|
| author | Zhou, Yiran Wang, Yingyu Huang, Shoudong Zhao, Liang |
| author_facet | Zhou, Yiran Wang, Yingyu Huang, Shoudong Zhao, Liang |
| contents | Multiview point cloud registration is a fundamental task for constructing globally consistent 3D models. Existing approaches typically rely on feature extraction and data association across multiple point clouds; however, these processes are challenging to obtain global optimal solution in complex environments. In this paper, we introduce a novel correspondence-free multiview point cloud registration method. Specifically, we represent the global map as a depth map and leverage raw depth information to formulate a non-linear least squares optimisation that jointly estimates poses of point clouds and the global map. Unlike traditional feature-based bundle adjustment methods, which rely on explicit feature extraction and data association, our method bypasses these challenges by associating multi-frame point clouds with a global depth map through their corresponding poses. This data association is implicitly incorporated and dynamically refined during the optimisation process. Extensive evaluations on real-world datasets demonstrate that our method outperforms state-of-the-art approaches in accuracy, particularly in challenging environments where feature extraction and data association are difficult. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_18922 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Correspondence-Free Multiview Point Cloud Registration via Depth-Guided Joint Optimisation Zhou, Yiran Wang, Yingyu Huang, Shoudong Zhao, Liang Computer Vision and Pattern Recognition Robotics Multiview point cloud registration is a fundamental task for constructing globally consistent 3D models. Existing approaches typically rely on feature extraction and data association across multiple point clouds; however, these processes are challenging to obtain global optimal solution in complex environments. In this paper, we introduce a novel correspondence-free multiview point cloud registration method. Specifically, we represent the global map as a depth map and leverage raw depth information to formulate a non-linear least squares optimisation that jointly estimates poses of point clouds and the global map. Unlike traditional feature-based bundle adjustment methods, which rely on explicit feature extraction and data association, our method bypasses these challenges by associating multi-frame point clouds with a global depth map through their corresponding poses. This data association is implicitly incorporated and dynamically refined during the optimisation process. Extensive evaluations on real-world datasets demonstrate that our method outperforms state-of-the-art approaches in accuracy, particularly in challenging environments where feature extraction and data association are difficult. |
| title | Correspondence-Free Multiview Point Cloud Registration via Depth-Guided Joint Optimisation |
| topic | Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2506.18922 |