Author:
Chen Ying,Huang Dihe,Xu Shang,Liu Jianlin,Liu Yong
Abstract
Local image feature matching under large appearance, viewpoint, and distance changes is challenging yet important. Conventional methods detect and match tentative local features across the whole images, with heuristic consistency checks to guarantee reliable matches. In this paper, we introduce a novel Overlap Estimation method conditioned on image pairs with TRansformer, named OETR, to constrain local feature matching in the commonly visible region. OETR performs overlap estimation in a two step process of feature correlation and then overlap regression. As a preprocessing module, OETR can be plugged into any existing local feature detection and matching pipeline, to mitigate potential view angle or scale variance. Intensive experiments show that OETR can boost state of the art local feature matching performance substantially, especially for image pairs with small shared regions. The code will be publicly available at https://github.com/AbyssGaze/OETR.
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Cited by
7 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. FMAP: Learning robust and accurate local feature matching with anchor points;Expert Systems with Applications;2024-02
2. Adaptive Assignment for Geometry Aware Local Feature Matching;2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR);2023-06
3. PATS: Patch Area Transportation with Subdivision for Local Feature Matching;2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR);2023-06
4. Adaptive Spot-Guided Transformer for Consistent Local Feature Matching;2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR);2023-06
5. Find My Astronaut Photo: Automated Localization and Georectification of Astronaut Photography;2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW);2023-06