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

arXiv: https://arxiv.org/abs/2505.22284 · HTML: https://mlsanity.com/paper/2505.22284/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 53 references that are in the map.
- First posted on arXiv 28 May 2025.

## Builds on (most cited first, 23 of 23)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [MambaIR: A Simple Baseline for Image Restoration with State-Space Model](https://mlsanity.com/paper/2402.15648/) (2024)
- [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019)
- [Vision Language Models in Autonomous Driving: A Survey and Outlook](https://mlsanity.com/paper/2310.14414/) (2023)
- [AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation](https://mlsanity.com/paper/2403.14614/) (2024)
- [Real-world Noisy Image Denoising: A New Benchmark](https://mlsanity.com/paper/1804.02603/) (2018)
- [Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model](https://mlsanity.com/paper/2403.11157/) (2024)
- [A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends](https://mlsanity.com/paper/2410.15067/) (2024)
- [Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception](https://mlsanity.com/paper/2002.01155/) (2020)
- [Towards Effective Multiple-in-One Image Restoration: A Sequential and Prompt Learning Strategy](https://mlsanity.com/paper/2401.03379/) (2024)
- [Toward Real-world Single Image Deraining: A New Benchmark and Beyond](https://mlsanity.com/paper/2206.05514/) (2022)
- [From Sky to the Ground: A Large-scale Benchmark and Simple Baseline Towards Real Rain Removal](https://mlsanity.com/paper/2308.03867/) (2023)
- [Bilevel Fast Scene Adaptation for Low-Light Image Enhancement](https://mlsanity.com/paper/2306.01343/) (2023)
- [Prompt-based Ingredient-Oriented All-in-One Image Restoration](https://mlsanity.com/paper/2309.03063/) (2023)
- [Test-Time Degradation Adaptation for Open-Set Image Restoration](https://mlsanity.com/paper/2312.02197/) (2023)
- [Spatial-frequency Dual-Domain Feature Fusion Network for Low-Light Remote Sensing Image Enhancement](https://mlsanity.com/paper/2404.17400/) (2024)

## Built on by (most cited first, 1 of 1)

- [WeatherCycle: Unpaired Multi-Weather Restoration via Color Space Decoupled Cycle Learning](https://mlsanity.com/paper/2509.23150/) (2025)

## Abstract (arXiv)

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.