# Learning the Degradation Distribution for Blind Image Super-Resolution

arXiv: https://arxiv.org/abs/2203.04962 · HTML: https://mlsanity.com/paper/2203.04962/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 49 references that are in the map.
- First posted on arXiv 9 Mar 2022.

## Builds on (most cited first, 30 of 33)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Designing a Practical Degradation Model for Deep Blind Image Super-Resolution](https://mlsanity.com/paper/2103.14006/) (2021)
- [Accelerating the Super-Resolution Convolutional Neural Network](https://mlsanity.com/paper/1608.00367/) (2016)
- [Deep Unfolding Network for Image Super-Resolution](https://mlsanity.com/paper/2003.10428/) (2020)
- [Unprocessing Images for Learned Raw Denoising](https://mlsanity.com/paper/1811.11127/) (2018)
- [Learning a Single Convolutional Super-Resolution Network for Multiple Degradations](https://mlsanity.com/paper/1712.06116/) (2017)
- [Benchmarking Denoising Algorithms with Real Photographs](https://mlsanity.com/paper/1707.01313/) (2017)
- [Blind Super-Resolution With Iterative Kernel Correction](https://mlsanity.com/paper/1904.03377/) (2019)
- [Blind Super-Resolution Kernel Estimation using an Internal-GAN](https://mlsanity.com/paper/1909.06581/) (2019)
- [Unfolding the Alternating Optimization for Blind Super Resolution](https://mlsanity.com/paper/2010.02631/) (2020)
- [Frequency Separation for Real-World Super-Resolution](https://mlsanity.com/paper/1911.07850/) (2019)
- [Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernels](https://mlsanity.com/paper/1903.12529/) (2019)
- [Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction](https://mlsanity.com/paper/2111.07910/) (2021)
- [To learn image super-resolution, use a GAN to learn how to do image degradation first](https://mlsanity.com/paper/1807.11458/) (2018)
- [Blind Image Super-Resolution: A Survey and Beyond](https://mlsanity.com/paper/2107.03055/) (2021)
- [Unsupervised Real-world Image Super Resolution via Domain-distance Aware Training](https://mlsanity.com/paper/2004.01178/) (2020)
- [NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results](https://mlsanity.com/paper/2005.01996/) (2020)
- [Unpaired Image Super-Resolution using Pseudo-Supervision](https://mlsanity.com/paper/2002.11397/) (2020)
- [Flow-Guided Sparse Transformer for Video Deblurring](https://mlsanity.com/paper/2201.01893/) (2022)
- [RFormer: Transformer-based Generative Adversarial Network for Real Fundus Image Restoration on A New Clinical Benchmark](https://mlsanity.com/paper/2201.00466/) (2022)
- [Unsupervised Image Super-Resolution with an Indirect Supervised Path](https://mlsanity.com/paper/1910.02593/) (2019)
- [Deep Generative Adversarial Residual Convolutional Networks for Real-World Super-Resolution](https://mlsanity.com/paper/2005.00953/) (2020)

## Built on by (most cited first, 27 of 27)

- [InstructIR: High-Quality Image Restoration Following Human Instructions](https://mlsanity.com/paper/2401.16468/) (2024)
- [PromptIR: Prompting for All-in-One Blind Image Restoration](https://mlsanity.com/paper/2306.13090/) (2023)
- [Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey](https://mlsanity.com/paper/2308.09388/) (2023)
- [MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction](https://mlsanity.com/paper/2204.07908/) (2022)
- [DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation](https://mlsanity.com/paper/2410.18666/) (2024)
- [SeD: Semantic-Aware Discriminator for Image Super-Resolution](https://mlsanity.com/paper/2402.19387/) (2024)
- [Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-Resolution](https://mlsanity.com/paper/2305.18107/) (2023)
- [Human Guided Ground-truth Generation for Realistic Image Super-resolution](https://mlsanity.com/paper/2303.13069/) (2023)
- [Infrared Image Super-Resolution: Systematic Review, and Future Trends](https://mlsanity.com/paper/2212.12322/) (2022)
- [Synthesizing Realistic Image Restoration Training Pairs: A Diffusion Approach](https://mlsanity.com/paper/2303.06994/) (2023)
- [Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration](https://mlsanity.com/paper/2406.18516/) (2024)
- [End-to-end Alternating Optimization for Real-World Blind Super Resolution](https://mlsanity.com/paper/2308.08816/) (2023)
- [Learning Many-to-Many Mapping for Unpaired Real-World Image Super-resolution and Downscaling](https://mlsanity.com/paper/2310.04964/) (2023)
- [VCISR: Blind Single Image Super-Resolution with Video Compression Synthetic Data](https://mlsanity.com/paper/2311.00996/) (2023)
- [Blind Super-Resolution via Meta-learning and Markov Chain Monte Carlo Simulation](https://mlsanity.com/paper/2406.08896/) (2024)
- [Unsupervised Imaging Inverse Problems with Diffusion Distribution Matching](https://mlsanity.com/paper/2506.14605/) (2025)
- [Learning Data-Driven Vector-Quantized Degradation Model for Animation Video Super-Resolution](https://mlsanity.com/paper/2303.09826/) (2023)
- [SuperInpaint: Learning Detail-Enhanced Attentional Implicit Representation for Super-resolutional Image Inpainting](https://mlsanity.com/paper/2307.14489/) (2023)
- [Reference-based Restoration of Digitized Analog Videotapes](https://mlsanity.com/paper/2310.14926/) (2023)
- [Bridging the Domain Gap: A Simple Domain Matching Method for Reference-based Image Super-Resolution in Remote Sensing](https://mlsanity.com/paper/2401.15944/) (2024)
- [Navigating Beyond Dropout: An Intriguing Solution Towards Generalizable Image Super Resolution](https://mlsanity.com/paper/2402.18929/) (2024)
- [DCS-RISR: Dynamic Channel Splitting for Efficient Real-world Image Super-Resolution](https://mlsanity.com/paper/2212.07613/) (2022)
- [Toward Real World Stereo Image Super-Resolution via Hybrid Degradation Model and Discriminator for Implied Stereo Image Information](https://mlsanity.com/paper/2312.07934/) (2023)
- [Analyzing the Feature Extractor Networks for Face Image Synthesis](https://mlsanity.com/paper/2406.02153/) (2024)
- [Deep Learning Empowered Super-Resolution: A Comprehensive Survey and Future Prospects](https://mlsanity.com/paper/2509.22692/) (2025)
- [RAW-Domain Degradation Models for Realistic Smartphone Super-Resolution](https://mlsanity.com/paper/2603.12493/) (2026)
- [Style-Driven Data Synthesis and Degradation-Aware Enhancement for Ultrasound Image Restoration](https://mlsanity.com/paper/2609.35120/) (2026)

## Abstract (arXiv)

Synthetic high-resolution (HR) & low-resolution (LR) pairs are widely used in existing super-resolution (SR) methods. To avoid the domain gap between synthetic and test images, most previous methods try to adaptively learn the synthesizing (degrading) process via a deterministic model. However, some degradations in real scenarios are stochastic and cannot be determined by the content of the image. These deterministic models may fail to model the random factors and content-independent parts of degradations, which will limit the performance of the following SR models. In this paper, we propose a probabilistic degradation model (PDM), which studies the degradation D as a random variable, and learns its distribution by modeling the mapping from a priori random variable z to D. Compared with previous deterministic degradation models, PDM could model more diverse degradations and generate HR-LR pairs that may better cover the various degradations of test images, and thus prevent the SR model from over-fitting to specific ones. Extensive experiments have demonstrated that our degradation model can help the SR model achieve better performance on different datasets. The source codes are released at urlgit@github.com:greatlog/UnpairedSR.git.