Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2021
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2104.00947 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929368185438208 |
|---|---|
| author | Shen, Xuelun Hu, Qian Li, Xin Wang, Cheng |
| author_facet | Shen, Xuelun Hu, Qian Li, Xin Wang, Cheng |
| contents | This paper presents a matching network to establish point correspondence between images. We propose a Multi-Arm Network (MAN) to learn region overlap and depth, which can greatly improve the keypoint matching robustness while bringing little computational cost during the inference stage. Another design that makes this framework different from many existing learning based pipelines that require re-training when a different keypoint detector is adopted, our network can directly work with different keypoint detectors without such a time-consuming re-training process. Comprehensive experiments conducted on outdoor and indoor datasets demonstrated that our proposed MAN outperforms state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2104_00947 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | A Detector-oblivious Multi-arm Network for Keypoint Matching Shen, Xuelun Hu, Qian Li, Xin Wang, Cheng Computer Vision and Pattern Recognition This paper presents a matching network to establish point correspondence between images. We propose a Multi-Arm Network (MAN) to learn region overlap and depth, which can greatly improve the keypoint matching robustness while bringing little computational cost during the inference stage. Another design that makes this framework different from many existing learning based pipelines that require re-training when a different keypoint detector is adopted, our network can directly work with different keypoint detectors without such a time-consuming re-training process. Comprehensive experiments conducted on outdoor and indoor datasets demonstrated that our proposed MAN outperforms state-of-the-art methods. |
| title | A Detector-oblivious Multi-arm Network for Keypoint Matching |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2104.00947 |