# Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction

arXiv: https://arxiv.org/abs/2310.19011 · HTML: https://mlsanity.com/paper/2310.19011/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 68 references that are in the map.
- First posted on arXiv 29 Oct 2023.

## Builds on (most cited first, 30 of 44)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model](https://mlsanity.com/paper/2212.00490/) (2022)
- [Designing a Practical Degradation Model for Deep Blind Image Super-Resolution](https://mlsanity.com/paper/2103.14006/) (2021)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Improving Diffusion Models for Inverse Problems using Manifold Constraints](https://mlsanity.com/paper/2206.00941/) (2022)
- [Efficient Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2204.02610/) (2022)
- [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](https://mlsanity.com/paper/1704.03915/) (2017)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models](https://mlsanity.com/paper/2104.14951/) (2021)
- [Towards Stable Test-Time Adaptation in Dynamic Wild World](https://mlsanity.com/paper/2302.12400/) (2023)
- [Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model](https://mlsanity.com/paper/1904.00523/) (2019)
- [MEMO: Test Time Robustness via Adaptation and Augmentation](https://mlsanity.com/paper/2110.09506/) (2021)
- [Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform](https://mlsanity.com/paper/1804.02815/) (2018)
- ["Zero-Shot" Super-Resolution using Deep Internal Learning](https://mlsanity.com/paper/1712.06087/) (2017)
- [Contrastive Test-Time Adaptation](https://mlsanity.com/paper/2204.10377/) (2022)
- [Unprocessing Images for Learned Raw Denoising](https://mlsanity.com/paper/1811.11127/) (2018)
- [Component Divide-and-Conquer for Real-World Image Super-Resolution](https://mlsanity.com/paper/2008.01928/) (2020)
- [Blind Super-Resolution With Iterative Kernel Correction](https://mlsanity.com/paper/1904.03377/) (2019)

## Built on by (most cited first, 18 of 18)

- [Test-Time Model Adaptation with Only Forward Passes](https://mlsanity.com/paper/2404.01650/) (2024)
- [Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models](https://mlsanity.com/paper/2410.12790/) (2024)
- [Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models](https://mlsanity.com/paper/2501.18592/) (2025)
- [Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting](https://mlsanity.com/paper/2403.11491/) (2024)
- [Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation](https://mlsanity.com/paper/2402.17316/) (2024)
- [Test-time Adaptation for Regression by Subspace Alignment](https://mlsanity.com/paper/2410.03263/) (2024)
- [Test-Time Model Adaptation for Quantized Neural Networks](https://mlsanity.com/paper/2508.02180/) (2025)
- [Self-Bootstrapping for Versatile Test-Time Adaptation](https://mlsanity.com/paper/2504.08010/) (2025)
- [Test-time Adaptation for Foundation Medical Segmentation Model without Parametric Updates](https://mlsanity.com/paper/2504.02008/) (2025)
- [Test-time adaptation for image compression with distribution regularization](https://mlsanity.com/paper/2410.12191/) (2024)
- [Test-time Training for Hyperspectral Image Super-resolution](https://mlsanity.com/paper/2409.08667/) (2024)
- [Continual Test-Time Adaptation for Single Image Defocus Deblurring via Causal Siamese Networks](https://mlsanity.com/paper/2501.09052/) (2025)
- [Mitigating Long-Tail Bias in HOI Detection via Adaptive Diversity Cache](https://mlsanity.com/paper/2511.18811/) (2025)
- [NTIRE 2024 Challenge on Stereo Image Super-Resolution: Methods and Results](https://mlsanity.com/paper/2409.16947/) (2024)
- [High-Resolution Be Aware! Improving the Self-Supervised Real-World Super-Resolution](https://mlsanity.com/paper/2411.16175/) (2024)
- [Unsupervised Image Super-Resolution Reconstruction Based on Real-World Degradation Patterns](https://mlsanity.com/paper/2506.17027/) (2025)
- [Stabilizing Test-Time Adaptation of High-Dimensional Simulation Surrogates via D-Optimal Statistics](https://mlsanity.com/paper/2602.15820/) (2026)
- [Language-Assisted Super-Resolution from Real-World Low-Resolution Patches](https://mlsanity.com/paper/2606.31363/) (2026)

## Abstract (arXiv)

Image super-resolution (SR) aims to learn a mapping from low-resolution (LR) to high-resolution (HR) using paired HR-LR training images. Conventional SR methods typically gather the paired training data by synthesizing LR images from HR images using a predetermined degradation model, e.g., Bicubic down-sampling. However, the realistic degradation type of test images may mismatch with the training-time degradation type due to the dynamic changes of the real-world scenarios, resulting in inferior-quality SR images. To address this, existing methods attempt to estimate the degradation model and train an image-specific model, which, however, is quite time-consuming and impracticable to handle rapidly changing domain shifts. Moreover, these methods largely concentrate on the estimation of one degradation type (e.g., blur degradation), overlooking other degradation types like noise and JPEG in real-world test-time scenarios, thus limiting their practicality. To tackle these problems, we present an efficient test-time adaptation framework for SR, named SRTTA, which is able to quickly adapt SR models to test domains with different/unknown degradation types. Specifically, we design a second-order degradation scheme to construct paired data based on the degradation type of the test image, which is predicted by a pre-trained degradation classifier. Then, we adapt the SR model by implementing feature-level reconstruction learning from the initial test image to its second-order degraded counterparts, which helps the SR model generate plausible HR images. Extensive experiments are conducted on newly synthesized corrupted DIV2K datasets with 8 different degradations and several real-world datasets, demonstrating that our SRTTA framework achieves an impressive improvement over existing methods with satisfying speed. The source code is available at https://github.com/DengZeshuai/SRTTA.