SDFReg: Learning Signed Distance Functions for Point Cloud Registration
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913191632568320 |
|---|---|
| author | Zhang, Leida Lu, Zhengda Liu, Kai Wang, Yiqun |
| author_facet | Zhang, Leida Lu, Zhengda Liu, Kai Wang, Yiqun |
| contents | Learning-based point cloud registration methods can handle clean point clouds well, while it is still challenging to generalize to noisy, partial, and density-varying point clouds. To this end, we propose a novel point cloud registration framework for these imperfect point clouds. By introducing a neural implicit representation, we replace the problem of rigid registration between point clouds with a registration problem between the point cloud and the neural implicit function. We then propose to alternately optimize the implicit function and the registration between the implicit function and point cloud. In this way, point cloud registration can be performed in a coarse-to-fine manner. By fully capitalizing on the capabilities of the neural implicit function without computing point correspondences, our method showcases remarkable robustness in the face of challenges such as noise, incompleteness, and density changes of point clouds. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2304_08929 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | SDFReg: Learning Signed Distance Functions for Point Cloud Registration Zhang, Leida Lu, Zhengda Liu, Kai Wang, Yiqun Computer Vision and Pattern Recognition Learning-based point cloud registration methods can handle clean point clouds well, while it is still challenging to generalize to noisy, partial, and density-varying point clouds. To this end, we propose a novel point cloud registration framework for these imperfect point clouds. By introducing a neural implicit representation, we replace the problem of rigid registration between point clouds with a registration problem between the point cloud and the neural implicit function. We then propose to alternately optimize the implicit function and the registration between the implicit function and point cloud. In this way, point cloud registration can be performed in a coarse-to-fine manner. By fully capitalizing on the capabilities of the neural implicit function without computing point correspondences, our method showcases remarkable robustness in the face of challenges such as noise, incompleteness, and density changes of point clouds. |
| title | SDFReg: Learning Signed Distance Functions for Point Cloud Registration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2304.08929 |