SAMatcher: Co-Visibility Modeling with Segment Anything for Robust Feature Matching 事件

SAMatcher: Co-Visibility Modeling with Segment Anything for Robust Feature Matching arXiv:2606.03406v1 Announce Type: new Abstract: Reliable correspondence estimation is a fundamental problem in image processing, underpinning applications such as Structure from Motion, visual localization, and image registration. Existing learning-based methods have significantly improved local feature representations, yet most still operate at the pixel or patch level and lack explicit modeling of regions that