From Controlled Scenarios to Real-World: Cross-Domain Degradation Pattern Matching for All-in-One Image Restoration

TL;DR

This paper introduces UDAIR, a domain-adaptive framework for All-in-One Image Restoration that effectively bridges the gap between controlled training data and real-world scenarios, improving degradation pattern recognition and restoration quality.

Contribution

The paper proposes a novel UDAIR framework with a codebook for degradation pattern learning, cross-sample contrastive learning, and domain adaptation strategies for robust real-world image restoration.

Findings

UDAIR achieves state-of-the-art results on 10 datasets.

The codebook effectively captures diverse degradation patterns.

Test-time adaptation improves real-world generalization.

Abstract

As a fundamental imaging task, All-in-One Image Restoration (AiOIR) aims to achieve image restoration caused by multiple degradation patterns via a single model with unified parameters. Although existing AiOIR approaches obtain promising performance in closed and controlled scenarios, they still suffered from considerable performance reduction in real-world scenarios since the gap of data distributions between the training samples (source domain) and real-world test samples (target domain) can lead inferior degradation awareness ability. To address this issue, a Unified Domain-Adaptive Image Restoration (UDAIR) framework is proposed to effectively achieve AiOIR by leveraging the learned knowledge from source domain to target domain. To improve the degradation identification, a codebook is designed to learn a group of discrete embeddings to denote the degradation patterns, and the cross-sample contrastive learning mechanism is further proposed to capture shared features from different samples of certain degradation. To bridge the data gap, a domain adaptation strategy is proposed to build the feature projection between the source and target domains by dynamically aligning their codebook embeddings, and a correlation alignment-based test-time adaptation mechanism is designed to fine-tune the alignment discrepancies by tightening the degradation embeddings to the corresponding cluster center in the source domain. Experimental results on 10 open-source datasets demonstrate that UDAIR achieves new state-of-the-art performance for the AiOIR task. Most importantly, the feature cluster validate the degradation identification under unknown conditions, and qualitative comparisons showcase robust generalization to real-world scenarios.