MCI-Net: A Robust Multi-Domain Context Integration Network for Point Cloud Registration
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918265372016640 |
|---|---|
| author | Lin, Shuyuan Peng, Wenwu Huang, Junjie Qi, Qiang Wang, Miaohui Weng, Jian |
| author_facet | Lin, Shuyuan Peng, Wenwu Huang, Junjie Qi, Qiang Wang, Miaohui Weng, Jian |
| contents | Robust and discriminative feature learning is critical for high-quality point cloud registration. However, existing deep learning-based methods typically rely on Euclidean neighborhood-based strategies for feature extraction, which struggle to effectively capture the implicit semantics and structural consistency in point clouds. To address these issues, we propose a multi-domain context integration network (MCI-Net) that improves feature representation and registration performance by aggregating contextual cues from diverse domains. Specifically, we propose a graph neighborhood aggregation module, which constructs a global graph to capture the overall structural relationships within point clouds. We then propose a progressive context interaction module to enhance feature discriminability by performing intra-domain feature decoupling and inter-domain context interaction. Finally, we design a dynamic inlier selection method that optimizes inlier weights using residual information from multiple iterations of pose estimation, thereby improving the accuracy and robustness of registration. Extensive experiments on indoor RGB-D and outdoor LiDAR datasets show that the proposed MCI-Net significantly outperforms existing state-of-the-art methods, achieving the highest registration recall of 96.4\% on 3DMatch. Source code is available at http://www.linshuyuan.com. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_23472 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MCI-Net: A Robust Multi-Domain Context Integration Network for Point Cloud Registration Lin, Shuyuan Peng, Wenwu Huang, Junjie Qi, Qiang Wang, Miaohui Weng, Jian Computer Vision and Pattern Recognition Robust and discriminative feature learning is critical for high-quality point cloud registration. However, existing deep learning-based methods typically rely on Euclidean neighborhood-based strategies for feature extraction, which struggle to effectively capture the implicit semantics and structural consistency in point clouds. To address these issues, we propose a multi-domain context integration network (MCI-Net) that improves feature representation and registration performance by aggregating contextual cues from diverse domains. Specifically, we propose a graph neighborhood aggregation module, which constructs a global graph to capture the overall structural relationships within point clouds. We then propose a progressive context interaction module to enhance feature discriminability by performing intra-domain feature decoupling and inter-domain context interaction. Finally, we design a dynamic inlier selection method that optimizes inlier weights using residual information from multiple iterations of pose estimation, thereby improving the accuracy and robustness of registration. Extensive experiments on indoor RGB-D and outdoor LiDAR datasets show that the proposed MCI-Net significantly outperforms existing state-of-the-art methods, achieving the highest registration recall of 96.4\% on 3DMatch. Source code is available at http://www.linshuyuan.com. |
| title | MCI-Net: A Robust Multi-Domain Context Integration Network for Point Cloud Registration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.23472 |