Adaptive Blind All-in-One Image Restoration

TL;DR

ABAIR is an adaptive blind image restoration model that effectively handles multiple and unseen degradations by integrating a segmentation head, low-rank adapters, and a degradation estimator, outperforming state-of-the-art methods.

Contribution

The paper introduces ABAIR, a novel adaptive model that generalizes to unseen distortions and efficiently incorporates new degradations with minimal additional training.

Findings

Surpasses state-of-the-art on multiple IR tasks

Demonstrates strong generalization to unseen distortions

Efficiently adapts to complex degradation scenarios

Abstract

Blind all-in-one image restoration models aim to recover a high-quality image from an input degraded with unknown distortions. However, these models require all the possible degradation types to be defined during the training stage while showing limited generalization to unseen degradations, which limits their practical application in complex cases. In this paper, we introduce ABAIR, a simple yet effective adaptive blind all-in-one restoration model that not only handles multiple degradations and generalizes well to unseen distortions but also efficiently integrates new degradations by training only a small subset of parameters. We first train our baseline model on a large dataset of natural images with multiple synthetic degradations. To enhance its ability to recognize distortions, we incorporate a segmentation head that estimates per-pixel degradation types. Second, we adapt our initial model to varying image restoration tasks using independent low-rank adapters. Third, we learn to adaptively combine adapters to versatile images via a flexible and lightweight degradation estimator. This specialize-then-merge approach is both powerful in addressing specific distortions and flexible in adapting to complex tasks. Moreover, our model not only surpasses state-of-the-art performance on five- and three-task IR setups but also demonstrates superior generalization to unseen degradations and composite distortions.