# Unsupervised Degradation Learning for Single Image Super-Resolution

arXiv: https://arxiv.org/abs/1812.04240 · HTML: https://mlsanity.com/paper/1812.04240/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Dec 2018.

## Built on by (most cited first, 9 of 9)

- [Real-World Single Image Super-Resolution: A Brief Review](https://mlsanity.com/paper/2103.02368/) (2021)
- [Toward Real-World Super-Resolution via Adaptive Downsampling Models](https://mlsanity.com/paper/2109.03444/) (2021)
- [Towards Lightweight Super-Resolution with Dual Regression Learning](https://mlsanity.com/paper/2207.07929/) (2022)
- [Generative Adversarial Networks for Image Super-Resolution: A Survey](https://mlsanity.com/paper/2204.13620/) (2022)
- [ICF-SRSR: Invertible scale-Conditional Function for Self-Supervised Real-world Single Image Super-Resolution](https://mlsanity.com/paper/2307.12751/) (2023)
- [Unpaired Optical Coherence Tomography Angiography Image Super-Resolution via Frequency-Aware Inverse-Consistency GAN](https://mlsanity.com/paper/2309.17269/) (2023)
- [Real-World Image Super Resolution via Unsupervised Bi-directional Cycle Domain Transfer Learning based Generative Adversarial Network](https://mlsanity.com/paper/2211.10563/) (2022)
- [Perceptual Image Restoration with High-Quality Priori and Degradation Learning](https://mlsanity.com/paper/2103.03010/) (2021)
- [CoT-MISR:Marrying Convolution and Transformer for Multi-Image Super-Resolution](https://mlsanity.com/paper/2303.06548/) (2023)

## Abstract (arXiv)

Deep Convolution Neural Networks (CNN) have achieved significant performance on single image super-resolution (SR) recently. However, existing CNN-based methods use artificially synthetic low-resolution (LR) and high-resolution (HR) image pairs to train networks, which cannot handle real-world cases since the degradation from HR to LR is much more complex than manually designed. To solve this problem, we propose a real-world LR images guided bi-cycle network for single image super-resolution, in which the bidirectional structural consistency is exploited to train both the degradation and SR reconstruction networks in an unsupervised way. Specifically, we propose a degradation network to model the real-world degradation process from HR to LR via generative adversarial networks, and these generated realistic LR images paired with real-world HR images are exploited for training the SR reconstruction network, forming the first cycle. Then in the second reverse cycle, consistency of real-world LR images are exploited to further stabilize the training of SR reconstruction and degradation networks. Extensive experiments on both synthetic and real-world images demonstrate that the proposed algorithm performs favorably against state-of-the-art single image SR methods.