RARE: Refine Any Registration of Pairwise Point Clouds via Zero-Shot Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909706861150208 |
|---|---|
| author | Zheng, Chengyu Huang, Jin Chen, Honghua Wei, Mingqiang |
| author_facet | Zheng, Chengyu Huang, Jin Chen, Honghua Wei, Mingqiang |
| contents | Recent research leveraging large-scale pretrained diffusion models has demonstrated the potential of using diffusion features to establish semantic correspondences in images. Inspired by advancements in diffusion-based techniques, we propose a novel zero-shot method for refining point cloud registration algorithms. Our approach leverages correspondences derived from depth images to enhance point feature representations, eliminating the need for a dedicated training dataset. Specifically, we first project the point cloud into depth maps from multiple perspectives and extract implicit knowledge from a pretrained diffusion network as depth diffusion features. These features are then integrated with geometric features obtained from existing methods to establish more accurate correspondences between point clouds. By leveraging these refined correspondences, our approach achieves significantly improved registration accuracy. Extensive experiments demonstrate that our method not only enhances the performance of existing point cloud registration techniques but also exhibits robust generalization capabilities across diverse datasets. Codes are available at https://github.com/zhengcy-lambo/RARE.git. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_19950 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RARE: Refine Any Registration of Pairwise Point Clouds via Zero-Shot Learning Zheng, Chengyu Huang, Jin Chen, Honghua Wei, Mingqiang Computer Vision and Pattern Recognition Artificial Intelligence Recent research leveraging large-scale pretrained diffusion models has demonstrated the potential of using diffusion features to establish semantic correspondences in images. Inspired by advancements in diffusion-based techniques, we propose a novel zero-shot method for refining point cloud registration algorithms. Our approach leverages correspondences derived from depth images to enhance point feature representations, eliminating the need for a dedicated training dataset. Specifically, we first project the point cloud into depth maps from multiple perspectives and extract implicit knowledge from a pretrained diffusion network as depth diffusion features. These features are then integrated with geometric features obtained from existing methods to establish more accurate correspondences between point clouds. By leveraging these refined correspondences, our approach achieves significantly improved registration accuracy. Extensive experiments demonstrate that our method not only enhances the performance of existing point cloud registration techniques but also exhibits robust generalization capabilities across diverse datasets. Codes are available at https://github.com/zhengcy-lambo/RARE.git. |
| title | RARE: Refine Any Registration of Pairwise Point Clouds via Zero-Shot Learning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2507.19950 |