Affine-based Deformable Attention and Selective Fusion for Semi-dense Matching
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911884756647936 |
|---|---|
| author | Chen, Hongkai Luo, Zixin Tian, Yurun Bai, Xuyang Wang, Ziyu Zhou, Lei Zhen, Mingmin Fang, Tian McKinnon, David Tsin, Yanghai Quan, Long |
| author_facet | Chen, Hongkai Luo, Zixin Tian, Yurun Bai, Xuyang Wang, Ziyu Zhou, Lei Zhen, Mingmin Fang, Tian McKinnon, David Tsin, Yanghai Quan, Long |
| contents | Identifying robust and accurate correspondences across images is a fundamental problem in computer vision that enables various downstream tasks. Recent semi-dense matching methods emphasize the effectiveness of fusing relevant cross-view information through Transformer. In this paper, we propose several improvements upon this paradigm. Firstly, we introduce affine-based local attention to model cross-view deformations. Secondly, we present selective fusion to merge local and global messages from cross attention. Apart from network structure, we also identify the importance of enforcing spatial smoothness in loss design, which has been omitted by previous works. Based on these augmentations, our network demonstrate strong matching capacity under different settings. The full version of our network achieves state-of-the-art performance among semi-dense matching methods at a similar cost to LoFTR, while the slim version reaches LoFTR baseline's performance with only 15% computation cost and 18% parameters. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_13874 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Affine-based Deformable Attention and Selective Fusion for Semi-dense Matching Chen, Hongkai Luo, Zixin Tian, Yurun Bai, Xuyang Wang, Ziyu Zhou, Lei Zhen, Mingmin Fang, Tian McKinnon, David Tsin, Yanghai Quan, Long Computer Vision and Pattern Recognition Identifying robust and accurate correspondences across images is a fundamental problem in computer vision that enables various downstream tasks. Recent semi-dense matching methods emphasize the effectiveness of fusing relevant cross-view information through Transformer. In this paper, we propose several improvements upon this paradigm. Firstly, we introduce affine-based local attention to model cross-view deformations. Secondly, we present selective fusion to merge local and global messages from cross attention. Apart from network structure, we also identify the importance of enforcing spatial smoothness in loss design, which has been omitted by previous works. Based on these augmentations, our network demonstrate strong matching capacity under different settings. The full version of our network achieves state-of-the-art performance among semi-dense matching methods at a similar cost to LoFTR, while the slim version reaches LoFTR baseline's performance with only 15% computation cost and 18% parameters. |
| title | Affine-based Deformable Attention and Selective Fusion for Semi-dense Matching |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.13874 |