Saved in:
Bibliographic Details
Main Authors: Fan, Junyu, Liao, Chuanlin, Lin, Yi
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.22284
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909626047397888
author Fan, Junyu
Liao, Chuanlin
Lin, Yi
author_facet Fan, Junyu
Liao, Chuanlin
Lin, Yi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_22284
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Controlled Scenarios to Real-World: Cross-Domain Degradation Pattern Matching for All-in-One Image Restoration
Fan, Junyu
Liao, Chuanlin
Lin, Yi
Computer Vision and Pattern Recognition
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.
title From Controlled Scenarios to Real-World: Cross-Domain Degradation Pattern Matching for All-in-One Image Restoration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.22284