Abstract
Image restoration aims to recover high quality images from inputs degraded by various factors, such as adverse weather, blur, or low light. While recent studies have shown remarkable progress across individual or unified restoration tasks, they still suffer from limited generalization and inefficiency when handling unknown or composite degradations. To address these limitations, we propose RAR, a Restore, Assess and Repeat process, that integrates Image Quality Assessment (IQA) and Image Restoration (IR) into a unified framework to iteratively and efficiently achieve high quality image restoration. Specifically, we introduce a restoration process that operates entirely in the latent domain to jointly perform degradation identification, image restoration, and quality verification. The resulting model is fully trainable end to end and allows for an all-in-one assess and restore approach that dynamically adapts the restoration process. Also, the tight integration of IQA and IR into a unified model minimizes the latency and information loss that typically arises from keeping the two modules disjoint, (e.g. during image and/or text decoding). Extensive experiments show that our approach consistent improvements under single, unknown and composite degradations, thereby establishing a new state-of-the-art.
Abstract (translated)
图像恢复旨在从受恶劣天气、模糊或低光照等多种因素退化的输入中重建高质量图像。尽管近期研究在单一或统一恢复任务上取得了显著进展，但在处理未知或复合退化时仍存在泛化能力有限和效率低下的问题。为克服这些局限，我们提出RAR（Restore, Assess and Repeat）流程，将图像质量评估（IQA）与图像恢复（IR）集成到统一框架中，通过迭代方式高效实现高质量图像恢复。具体而言，我们引入完全在潜在域运行的恢复流程，协同完成退化识别、图像恢复与质量验证。所得模型支持端到端全流程训练，实现动态适应恢复过程的“一体化评估-恢复”方案。同时，IQA与IR的紧密集成最小了传统分离模块（如图像/文本解码阶段）带来的延迟与信息损失。大量实验表明，该方法在单一、未知及复合退化场景下均持续提升性能，确立了新的最先进水平。
URL
https://arxiv.org/abs/2603.26385
