Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.05122 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915664317382656 |
|---|---|
| author | Li, Xi Rao, Tong Pan, Cihui |
| author_facet | Li, Xi Rao, Tong Pan, Cihui |
| contents | Recent feature matching methods have achieved remarkable performance but lack efficiency consideration. In this paper, we revisit the mainstream detector-free matching pipeline and improve all its stages considering both accuracy and efficiency. We propose an Efficient Deep feature Matching network, EDM. We first adopt a deeper CNN with fewer dimensions to extract multi-level features. Then we present a Correlation Injection Module that conducts feature transformation on high-level deep features, and progressively injects feature correlations from global to local for efficient multi-scale feature aggregation, improving both speed and performance. In the refinement stage, a novel lightweight bidirectional axis-based regression head is designed to directly predict subpixel-level correspondences from latent features, avoiding the significant computational cost of explicitly locating keypoints on high-resolution local feature heatmaps. Moreover, effective selection strategies are introduced to enhance matching accuracy. Extensive experiments show that our EDM achieves competitive matching accuracy on various benchmarks and exhibits excellent efficiency, offering valuable best practices for real-world applications. The code is available at https://github.com/chicleee/EDM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_05122 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EDM: Efficient Deep Feature Matching Li, Xi Rao, Tong Pan, Cihui Computer Vision and Pattern Recognition Recent feature matching methods have achieved remarkable performance but lack efficiency consideration. In this paper, we revisit the mainstream detector-free matching pipeline and improve all its stages considering both accuracy and efficiency. We propose an Efficient Deep feature Matching network, EDM. We first adopt a deeper CNN with fewer dimensions to extract multi-level features. Then we present a Correlation Injection Module that conducts feature transformation on high-level deep features, and progressively injects feature correlations from global to local for efficient multi-scale feature aggregation, improving both speed and performance. In the refinement stage, a novel lightweight bidirectional axis-based regression head is designed to directly predict subpixel-level correspondences from latent features, avoiding the significant computational cost of explicitly locating keypoints on high-resolution local feature heatmaps. Moreover, effective selection strategies are introduced to enhance matching accuracy. Extensive experiments show that our EDM achieves competitive matching accuracy on various benchmarks and exhibits excellent efficiency, offering valuable best practices for real-world applications. The code is available at https://github.com/chicleee/EDM. |
| title | EDM: Efficient Deep Feature Matching |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.05122 |