Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.07607 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910253257326592 |
|---|---|
| author | Cheng, Zhixin Chen, Yujia Tao, Xujing Liao, Bohao Yin, Xiaotian Yin, Baoqun Zhang, Tianzhu |
| author_facet | Cheng, Zhixin Chen, Yujia Tao, Xujing Liao, Bohao Yin, Xiaotian Yin, Baoqun Zhang, Tianzhu |
| contents | Image-to-point cloud registration is often challenged by viewpoint changes, cross-modal discrepancies, and repetitive textures, which induce scale ambiguity and consequently lead to erroneous correspondences. Recent detection-free methods alleviate this issue by leveraging multi-scale features and transformer-based interactions. However, they still suffer from attention drift across layers and intra-scale inconsistencies, hindering precise registration. Inspired by human behavior, we propose a ``Focus--Sweep'' paradigm and develop a Hierarchical Focus--Sweep Interaction Module within an SSM-based framework to enhance multi-level cross-modal feature association. In addition, we introduce a Dynamic Layer Allocation Strategy that adaptively determines the iteration depth to better exploit geometric constraints and improve matching robustness. Extensive experiments and ablations on two benchmarks, RGB-D Scenes V2 and 7-Scenes, demonstrate that our approach achieves state-of-the-art performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_07607 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FS-I2P:A Hierarchical Focus-Sweep Registration Network with Dynamically Allocated Depth Cheng, Zhixin Chen, Yujia Tao, Xujing Liao, Bohao Yin, Xiaotian Yin, Baoqun Zhang, Tianzhu Computer Vision and Pattern Recognition Image-to-point cloud registration is often challenged by viewpoint changes, cross-modal discrepancies, and repetitive textures, which induce scale ambiguity and consequently lead to erroneous correspondences. Recent detection-free methods alleviate this issue by leveraging multi-scale features and transformer-based interactions. However, they still suffer from attention drift across layers and intra-scale inconsistencies, hindering precise registration. Inspired by human behavior, we propose a ``Focus--Sweep'' paradigm and develop a Hierarchical Focus--Sweep Interaction Module within an SSM-based framework to enhance multi-level cross-modal feature association. In addition, we introduce a Dynamic Layer Allocation Strategy that adaptively determines the iteration depth to better exploit geometric constraints and improve matching robustness. Extensive experiments and ablations on two benchmarks, RGB-D Scenes V2 and 7-Scenes, demonstrate that our approach achieves state-of-the-art performance. |
| title | FS-I2P:A Hierarchical Focus-Sweep Registration Network with Dynamically Allocated Depth |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.07607 |