# To learn image super-resolution, use a GAN to learn how to do image degradation first

arXiv: https://arxiv.org/abs/1807.11458 · HTML: https://mlsanity.com/paper/1807.11458/

## Key facts

- Cited by 94 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2018.

## Built on by (most cited first, 30 of 94)

- [Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution](https://mlsanity.com/paper/2203.14216/) (2022)
- [Blind Image Super-Resolution: A Survey and Beyond](https://mlsanity.com/paper/2107.03055/) (2021)
- [Deep Burst Super-Resolution](https://mlsanity.com/paper/2101.10997/) (2021)
- [CoSeR: Bridging Image and Language for Cognitive Super-Resolution](https://mlsanity.com/paper/2311.16512/) (2023)
- [Real-World Single Image Super-Resolution: A Brief Review](https://mlsanity.com/paper/2103.02368/) (2021)
- [Towards Realistic Data Generation for Real-World Super-Resolution](https://mlsanity.com/paper/2406.07255/) (2024)
- [Machine Unlearning for Image-to-Image Generative Models](https://mlsanity.com/paper/2402.00351/) (2024)
- [Deep Learning-based Face Super-Resolution: A Survey](https://mlsanity.com/paper/2101.03749/) (2021)
- [DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows](https://mlsanity.com/paper/2101.05796/) (2021)
- [Knowledge Distillation based Degradation Estimation for Blind Super-Resolution](https://mlsanity.com/paper/2211.16928/) (2022)
- [Learning the Degradation Distribution for Blind Image Super-Resolution](https://mlsanity.com/paper/2203.04962/) (2022)
- [A Comprehensive Review of Deep Learning-based Single Image Super-resolution](https://mlsanity.com/paper/2102.09351/) (2021)
- [AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos](https://mlsanity.com/paper/2206.07038/) (2022)
- [Image Super-Resolution with Text Prompt Diffusion](https://mlsanity.com/paper/2311.14282/) (2023)
- [Controllable and Guided Face Synthesis for Unconstrained Face Recognition](https://mlsanity.com/paper/2207.10180/) (2022)
- [Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances](https://mlsanity.com/paper/2209.13131/) (2022)
- [Entropy-driven Sampling and Training Scheme for Conditional Diffusion Generation](https://mlsanity.com/paper/2206.11474/) (2022)
- [WaveFace: Authentic Face Restoration with Efficient Frequency Recovery](https://mlsanity.com/paper/2403.12760/) (2024)
- [A Systematic Survey of Deep Learning-based Single-Image Super-Resolution](https://mlsanity.com/paper/2109.14335/) (2021)
- [Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning](https://mlsanity.com/paper/2403.02601/) (2024)
- [Learn from Unpaired Data for Image Restoration: A Variational Bayes Approach](https://mlsanity.com/paper/2204.10090/) (2022)
- [Survey on Deep Face Restoration: From Non-blind to Blind and Beyond](https://mlsanity.com/paper/2309.15490/) (2023)
- [Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction](https://mlsanity.com/paper/2310.19011/) (2023)
- [End-to-end Alternating Optimization for Blind Super Resolution](https://mlsanity.com/paper/2105.06878/) (2021)
- [Deep Face Restoration: A Survey](https://mlsanity.com/paper/2211.02831/) (2022)
- [Self-Supervised Deep Blind Video Super-Resolution](https://mlsanity.com/paper/2201.07422/) (2022)
- [One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution](https://mlsanity.com/paper/2506.15591/) (2025)
- [Toward Real-World Super-Resolution via Adaptive Downsampling Models](https://mlsanity.com/paper/2109.03444/) (2021)
- [Degrade is Upgrade: Learning Degradation for Low-light Image Enhancement](https://mlsanity.com/paper/2103.10621/) (2021)
- [Joint Motion Correction and Super Resolution for Cardiac Segmentation via Latent Optimisation](https://mlsanity.com/paper/2107.03887/) (2021)

## Abstract (arXiv)

This paper is on image and face super-resolution. The vast majority of prior work for this problem focus on how to increase the resolution of low-resolution images which are artificially generated by simple bilinear down-sampling (or in a few cases by blurring followed by down-sampling).We show that such methods fail to produce good results when applied to real-world low-resolution, low quality images. To circumvent this problem, we propose a two-stage process which firstly trains a High-to-Low Generative Adversarial Network (GAN) to learn how to degrade and downsample high-resolution images requiring, during training, only unpaired high and low-resolution images. Once this is achieved, the output of this network is used to train a Low-to-High GAN for image super-resolution using this time paired low- and high-resolution images. Our main result is that this network can be now used to efectively increase the quality of real-world low-resolution images. We have applied the proposed pipeline for the problem of face super-resolution where we report large improvement over baselines and prior work although the proposed method is potentially applicable to other object categories.