同时优化图像修复与匹配，零样本适配提升真实场景图像质量
MatRes: Zero-Shot Test-Time Model Adaptation for Simultaneous Matching and Restoration
- 联合优化修复与匹配，仅用一对高低质量图自适应更新轻量模块
- 相比单独使用修复或匹配模型，显著提升修复质量和对应点精度
- 无需训练、无需标注，适合多视角低质图像采集的实用场景
真实世界图像对常伴随严重退化和大视角变化，若独立处理图像修复与几何匹配，二者会相互干扰。本文提出 MatRes，一种零样本测试时自适应框架，通过仅使用一对低质与高质图像，联合提升修复质量与对应关系估计。该方法在对应位置强制条件相似性，仅更新轻量级模块，保持所有预训练组件冻结，无需离线训练或额外监督。大量实验表明，在多种组合下，MatRes 在修复与几何对齐方面均显著优于单独使用修复或匹配模型。该方法为用户在不同视角与画质下拍摄多张图像的真实场景提供了高效且普适的解决方案，有效缓解了匹配与修复间的相互干扰问题。
原文摘要 · Abstract (English)
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 corresponding locations, MatRes updates only lightweight modules while keeping all pretrained components frozen, requiring no offline training or additional supervision. Extensive experiments across diverse combinations show that MatRes yields significant gains in both restoration and geometric alignment compared to using either restoration or matching models alone. MatRes offers a practical and widely applicable solution for real-world scenarios where users commonly capture multiple images of a scene with varying viewpoints and quality, effectively addressing the often-overlooked mutual interference between matching and restoration.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。