MatRes: Zero-Shot Test-Time Model Adaptation for Simultaneous Matching and Restoration

arXiv:2604.10081v1 Announce Type: cross Abstract: Real-world image pairs often exhibit both severe degradations and large viewpoint changes, making image restoration and geometric matching mutually interfering tasks when treated independently. In this work, we propose MatRes, a zero-shot test-time adaptation framework that jointly improves restoration quality and correspondence estimation using only a single low-quality and high-quality image pair. By enforcing conditional similarity at correspo