AI RESEARCH
MatRes: Zero-Shot Test-Time Model Adaptation for Simultaneous Matching and Restoration
arXiv CS.AI
•
ArXi:2604.10081v1 Announce Type: cross 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.