Proxies for Distortion and Consistency with Applications for Real-World Image Restoration
This work addresses the problem of blind image restoration for researchers and practitioners by providing a first-of-its-kind framework, though it is incremental as it builds on existing methods like diffusion priors.
The paper tackles the challenge of designing and evaluating real-world image restoration algorithms without ground-truth images by proposing a suite of tools, including a degradation estimator for consistency and plug-and-play restoration, and no-reference proxy measures for ranking algorithms based on approximate MSE and LPIPS.
Real-world image restoration deals with the recovery of images suffering from an unknown degradation. This task is typically addressed while being given only degraded images, without their corresponding ground-truth versions. In this hard setting, designing and evaluating restoration algorithms becomes highly challenging. This paper offers a suite of tools that can serve both the design and assessment of real-world image restoration algorithms. Our work starts by proposing a trained model that predicts the chain of degradations a given real-world measured input has gone through. We show how this estimator can be used to approximate the consistency -- the match between the measurements and any proposed recovered image. We also use this estimator as a guiding force for the design of a simple and highly-effective plug-and-play real-world image restoration algorithm, leveraging a pre-trained diffusion-based image prior. Furthermore, this work proposes no-reference proxy measures of MSE and LPIPS, which, without access to the ground-truth images, allow ranking of real-world image restoration algorithms according to their (approximate) MSE and LPIPS. The proposed suite provides a versatile, first of its kind framework for evaluating and comparing blind image restoration algorithms in real-world scenarios.