# Test-Time Degradation Adaptation for Open-Set Image Restoration

arXiv: https://arxiv.org/abs/2312.02197 · HTML: https://mlsanity.com/paper/2312.02197/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 47 references that are in the map.
- First posted on arXiv 2 Dec 2023.

## Builds on (most cited first, 27 of 27)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Denoising Diffusion Restoration Models](https://mlsanity.com/paper/2201.11793/) (2022)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model](https://mlsanity.com/paper/2212.00490/) (2022)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [EnlightenGAN: Deep Light Enhancement without Paired Supervision](https://mlsanity.com/paper/1906.06972/) (2019)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [Noise2Void - Learning Denoising from Single Noisy Images](https://mlsanity.com/paper/1811.10980/) (2018)
- [DehazeNet: An End-to-End System for Single Image Haze Removal](https://mlsanity.com/paper/1601.07661/) (2016)
- [Perception Prioritized Training of Diffusion Models](https://mlsanity.com/paper/2204.00227/) (2022)
- ["Zero-Shot" Super-Resolution using Deep Internal Learning](https://mlsanity.com/paper/1712.06087/) (2017)
- [Noise2Self: Blind Denoising by Self-Supervision](https://mlsanity.com/paper/1901.11365/) (2019)
- [Generative Diffusion Prior for Unified Image Restoration and Enhancement](https://mlsanity.com/paper/2304.01247/) (2023)
- [Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation](https://mlsanity.com/paper/2103.00860/) (2021)
- ["Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-Priors](https://mlsanity.com/paper/1812.00467/) (2018)
- [PromptIR: Prompting for All-in-One Blind Image Restoration](https://mlsanity.com/paper/2306.13090/) (2023)
- [AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion](https://mlsanity.com/paper/2310.10123/) (2023)
- [Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptation](https://mlsanity.com/paper/2212.04145/) (2022)
- [MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation](https://mlsanity.com/paper/2204.12667/) (2022)
- [You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network](https://mlsanity.com/paper/2006.16829/) (2020)
- [TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation](https://mlsanity.com/paper/2303.16730/) (2023)
- [Multi-Scale Adaptive Network for Single Image Denoising](https://mlsanity.com/paper/2203.04313/) (2022)

## Built on by (most cited first, 17 of 17)

- [A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends](https://mlsanity.com/paper/2410.15067/) (2024)
- [MoE-DiffIR: Task-customized Diffusion Priors for Universal Compressed Image Restoration](https://mlsanity.com/paper/2407.10833/) (2024)
- [ClearAIR: A Human-Visual-Perception-Inspired All-in-One Image Restoration](https://mlsanity.com/paper/2601.02763/) (2026)
- [IRBridge: Solving Image Restoration Bridge with Pre-trained Generative Diffusion Models](https://mlsanity.com/paper/2505.24406/) (2025)
- [Test-time Adaptation for Cross-modal Retrieval with Query Shift](https://mlsanity.com/paper/2410.15624/) (2024)
- [Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration](https://mlsanity.com/paper/2406.18516/) (2024)
- [Adaptive Blind All-in-One Image Restoration](https://mlsanity.com/paper/2411.18412/) (2024)
- [Zero-Shot Low Light Image Enhancement with Diffusion Prior](https://mlsanity.com/paper/2412.13401/) (2024)
- [Test-Time Preference Optimization for Image Restoration](https://mlsanity.com/paper/2511.19169/) (2025)
- [Test-time Ego-Exo-centric Adaptation for Action Anticipation via Multi-Label Prototype Growing and Dual-Clue Consistency](https://mlsanity.com/paper/2603.09798/) (2026)
- [UDC-VIT: A Real-World Video Dataset for Under-Display Cameras](https://mlsanity.com/paper/2501.18545/) (2025)
- [From Controlled Scenarios to Real-World: Cross-Domain Degradation Pattern Matching for All-in-One Image Restoration](https://mlsanity.com/paper/2505.22284/) (2025)
- [Restoration Adaptation for Semantic Segmentation on Low Quality Images](https://mlsanity.com/paper/2602.14042/) (2026)
- [Expandable, Compressible, Mineable: Open-World Thermal Image Restoration](https://mlsanity.com/paper/2605.16967/) (2026)
- [Resolving Blind Inverse Problems under Dynamic Range Compression via Structured Forward Operator Modeling](https://mlsanity.com/paper/2603.01890/) (2026)
- [Zero-shot Low-Field MRI Enhancement via Diffusion-Based Adaptive Contrast Transport](https://mlsanity.com/paper/2603.01913/) (2026)
- [Self-supervised Dynamic Heterogeneous Degradation Modeling for Unified Zero-Shot Image Restoration](https://mlsanity.com/paper/2605.24593/) (2026)

## Abstract (arXiv)

In contrast to close-set scenarios that restore images from a predefined set of degradations, open-set image restoration aims to handle the unknown degradations that were unforeseen during the pretraining phase, which is less-touched as far as we know. This work study this challenging problem and reveal its essence as unidentified distribution shifts between the test and training data. Recently, test-time adaptation has emerged as a fundamental method to address this inherent disparities. Inspired by it, we propose a test-time degradation adaptation framework for open-set image restoration, which consists of three components, textiti.e., i) a pre-trained and degradation-agnostic diffusion model for generating clean images, ii) a test-time degradation adapter adapts the unknown degradations based on the input image during the testing phase, and iii) the adapter-guided image restoration guides the model through the adapter to produce the corresponding clean image. Through experiments on multiple degradations, we show that our method achieves comparable even better performance than those task-specific methods. The code is available at https://github.com/XLearning-SCU/2024-ICML-TAO.