Restore, Assess, Repeat: A Unified Framework for Iterative Image Restoration
This work addresses inefficiencies in image restoration for handling unknown or composite degradations, representing an incremental advancement with a novel integration approach.
The paper tackles the problem of limited generalization and inefficiency in image restoration for unknown or composite degradations by proposing RAR, a unified framework that iteratively integrates image quality assessment and restoration in the latent domain, achieving consistent improvements and establishing a new state-of-the-art.
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.