# Unsupervised Learning for Real-World Super-Resolution

arXiv: https://arxiv.org/abs/1909.09629 · HTML: https://mlsanity.com/paper/1909.09629/

## Key facts

- Cited by 64 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2019.

## Built on by (most cited first, 30 of 64)

- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Designing a Practical Degradation Model for Deep Blind Image Super-Resolution](https://mlsanity.com/paper/2103.14006/) (2021)
- [Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization](https://mlsanity.com/paper/2308.14469/) (2023)
- [Investigating Tradeoffs in Real-World Video Super-Resolution](https://mlsanity.com/paper/2111.12704/) (2021)
- [Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey](https://mlsanity.com/paper/2308.09388/) (2023)
- [Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution](https://mlsanity.com/paper/2203.14216/) (2022)
- [Deep Burst Super-Resolution](https://mlsanity.com/paper/2101.10997/) (2021)
- [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)
- [Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution](https://mlsanity.com/paper/2108.05302/) (2021)
- [Learned Smartphone ISP on Mobile NPUs with Deep Learning, Mobile AI 2021 Challenge: Report](https://mlsanity.com/paper/2105.07809/) (2021)
- [DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows](https://mlsanity.com/paper/2101.05796/) (2021)
- [Unveiling Hidden Details: A RAW Data-Enhanced Paradigm for Real-World Super-Resolution](https://mlsanity.com/paper/2411.10798/) (2024)
- [A Closer Look at Blind Super-Resolution: Degradation Models, Baselines, and Performance Upper Bounds](https://mlsanity.com/paper/2205.04910/) (2022)
- [Learn from Unpaired Data for Image Restoration: A Variational Bayes Approach](https://mlsanity.com/paper/2204.10090/) (2022)
- [SuperBench: A Super-Resolution Benchmark Dataset for Scientific Machine Learning](https://mlsanity.com/paper/2306.14070/) (2023)
- [Learning Distortion Invariant Representation for Image Restoration from A Causality Perspective](https://mlsanity.com/paper/2303.06859/) (2023)
- [From Face to Natural Image: Learning Real Degradation for Blind Image Super-Resolution](https://mlsanity.com/paper/2210.00752/) (2022)
- [Toward Real-World Super-Resolution via Adaptive Downsampling Models](https://mlsanity.com/paper/2109.03444/) (2021)
- [Learned Smartphone ISP on Mobile GPUs with Deep Learning, Mobile AI & AIM 2022 Challenge: Report](https://mlsanity.com/paper/2211.03885/) (2022)
- [MicroISP: Processing 32MP Photos on Mobile Devices with Deep Learning](https://mlsanity.com/paper/2211.06770/) (2022)
- [An Optimal Transport Perspective on Unpaired Image Super-Resolution](https://mlsanity.com/paper/2202.01116/) (2022)
- [Real-World Super-Resolution of Face-Images from Surveillance Cameras](https://mlsanity.com/paper/2102.03113/) (2021)
- [Bayesian Image Super-Resolution with Deep Modeling of Image Statistics](https://mlsanity.com/paper/2204.00623/) (2022)
- [Generative Adversarial Networks for Image Super-Resolution: A Survey](https://mlsanity.com/paper/2204.13620/) (2022)
- [Synthesizing Realistic Image Restoration Training Pairs: A Diffusion Approach](https://mlsanity.com/paper/2303.06994/) (2023)
- [BSRAW: Improving Blind RAW Image Super-Resolution](https://mlsanity.com/paper/2312.15487/) (2023)
- [Normalizing Flow as a Flexible Fidelity Objective for Photo-Realistic Super-resolution](https://mlsanity.com/paper/2111.03649/) (2021)
- [Generalized Real-World Super-Resolution through Adversarial Robustness](https://mlsanity.com/paper/2108.11505/) (2021)
- [Flexible Style Image Super-Resolution using Conditional Objective](https://mlsanity.com/paper/2201.04898/) (2022)

## Abstract (arXiv)

Most current super-resolution methods rely on low and high resolution image pairs to train a network in a fully supervised manner. However, such image pairs are not available in real-world applications. Instead of directly addressing this problem, most works employ the popular bicubic downsampling strategy to artificially generate a corresponding low resolution image. Unfortunately, this strategy introduces significant artifacts, removing natural sensor noise and other real-world characteristics. Super-resolution networks trained on such bicubic images therefore struggle to generalize to natural images. In this work, we propose an unsupervised approach for image super-resolution. Given only unpaired data, we learn to invert the effects of bicubic downsampling in order to restore the natural image characteristics present in the data. This allows us to generate realistic image pairs, faithfully reflecting the distribution of real-world images. Our super-resolution network can therefore be trained with direct pixel-wise supervision in the high resolution domain, while robustly generalizing to real input. We demonstrate the effectiveness of our approach in quantitative and qualitative experiments.