CodingHomo: Bootstrapping Deep Homography With Video Coding
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_ | 1866910912766541824 |
|---|---|
| author | Liu, Yike Li, Haipeng Liu, Shuaicheng Zeng, Bing |
| author_facet | Liu, Yike Li, Haipeng Liu, Shuaicheng Zeng, Bing |
| contents | Homography estimation is a fundamental task in computer vision with applications in diverse fields. Recent advances in deep learning have improved homography estimation, particularly with unsupervised learning approaches, offering increased robustness and generalizability. However, accurately predicting homography, especially in complex motions, remains a challenge. In response, this work introduces a novel method leveraging video coding, particularly by harnessing inherent motion vectors (MVs) present in videos. We present CodingHomo, an unsupervised framework for homography estimation. Our framework features a Mask-Guided Fusion (MGF) module that identifies and utilizes beneficial features among the MVs, thereby enhancing the accuracy of homography prediction. Additionally, the Mask-Guided Homography Estimation (MGHE) module is presented for eliminating undesired features in the coarse-to-fine homography refinement process. CodingHomo outperforms existing state-of-the-art unsupervised methods, delivering good robustness and generalizability. The code and dataset are available at: \href{github}{https://github.com/liuyike422/CodingHomo |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_12165 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CodingHomo: Bootstrapping Deep Homography With Video Coding Liu, Yike Li, Haipeng Liu, Shuaicheng Zeng, Bing Computer Vision and Pattern Recognition Homography estimation is a fundamental task in computer vision with applications in diverse fields. Recent advances in deep learning have improved homography estimation, particularly with unsupervised learning approaches, offering increased robustness and generalizability. However, accurately predicting homography, especially in complex motions, remains a challenge. In response, this work introduces a novel method leveraging video coding, particularly by harnessing inherent motion vectors (MVs) present in videos. We present CodingHomo, an unsupervised framework for homography estimation. Our framework features a Mask-Guided Fusion (MGF) module that identifies and utilizes beneficial features among the MVs, thereby enhancing the accuracy of homography prediction. Additionally, the Mask-Guided Homography Estimation (MGHE) module is presented for eliminating undesired features in the coarse-to-fine homography refinement process. CodingHomo outperforms existing state-of-the-art unsupervised methods, delivering good robustness and generalizability. The code and dataset are available at: \href{github}{https://github.com/liuyike422/CodingHomo |
| title | CodingHomo: Bootstrapping Deep Homography With Video Coding |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.12165 |