MESA: Matching Everything by Segmenting Anything. (arXiv:2401.16741v1 [cs.CV])

Feature matching is a crucial task in the field of computer vision, which
involves finding correspondences between images. Previous studies achieve
remarkable performance using learning-based feature comparison. However, the
pervasive presence of matching redundancy between images gives rise to
unnecessary and error-prone computations in these methods, imposing limitations
on their accuracy. To address this issue, we propose MESA, a novel approach to
establish precise area (or region) matches for efficient matching redundancy
reduction. MESA first leverages the advanced image understanding …

accuracy arxiv comparison computer computer vision cs.cv error everything feature images limitations mesa performance redundancy studies vision