# Unsupervised Image Super-Resolution with an Indirect Supervised Path

arXiv: https://arxiv.org/abs/1910.02593 · HTML: https://mlsanity.com/paper/1910.02593/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2019.

## Built on by (most cited first, 20 of 20)

- [Real-World Single Image Super-Resolution: A Brief Review](https://mlsanity.com/paper/2103.02368/) (2021)
- [Learning the Degradation Distribution for Blind Image Super-Resolution](https://mlsanity.com/paper/2203.04962/) (2022)
- [End-to-end Alternating Optimization for Blind Super Resolution](https://mlsanity.com/paper/2105.06878/) (2021)
- [Unaligned Image-to-Image Translation by Learning to Reweight](https://mlsanity.com/paper/2109.11736/) (2021)
- [Generative Adversarial Networks for Image Super-Resolution: A Survey](https://mlsanity.com/paper/2204.13620/) (2022)
- [Semi-Cycled Generative Adversarial Networks for Real-World Face Super-Resolution](https://mlsanity.com/paper/2205.03777/) (2022)
- [End-to-end Alternating Optimization for Real-World Blind Super Resolution](https://mlsanity.com/paper/2308.08816/) (2023)
- [Unsupervised Imaging Inverse Problems with Diffusion Distribution Matching](https://mlsanity.com/paper/2506.14605/) (2025)
- [Towards Real World HDRTV Reconstruction: A Data Synthesis-based Approach](https://mlsanity.com/paper/2211.03058/) (2022)
- [MR Slice Profile Estimation by Learning to Match Internal Patch Distributions](https://mlsanity.com/paper/2104.00100/) (2021)
- [Test-Time Adaptation for Super-Resolution: You Only Need to Overfit on a Few More Images](https://mlsanity.com/paper/2104.02663/) (2021)
- [An Unsupervised Framework for Joint MRI Super Resolution and Gibbs Artifact Removal](https://mlsanity.com/paper/2302.02849/) (2023)
- [Unpaired Optical Coherence Tomography Angiography Image Super-Resolution via Frequency-Aware Inverse-Consistency GAN](https://mlsanity.com/paper/2309.17269/) (2023)
- [Estimates of maize plant density from UAV RGB images using Faster-RCNN detection model: impact of the spatial resolution](https://mlsanity.com/paper/2105.11857/) (2021)
- [Real-World Single Image Super-Resolution Under Rainy Condition](https://mlsanity.com/paper/2206.08345/) (2022)
- [Enhanced Super-Resolution Training via Mimicked Alignment for Real-World Scenes](https://mlsanity.com/paper/2410.05410/) (2024)
- [Trainable Loss Weights in Super-Resolution](https://mlsanity.com/paper/2301.10575/) (2023)
- [A Novel Implicit Neural Representation for Volume Data](https://mlsanity.com/paper/2403.08566/) (2024)
- [Unsupervised Image Super-Resolution Reconstruction Based on Real-World Degradation Patterns](https://mlsanity.com/paper/2506.17027/) (2025)
- [Style-Driven Data Synthesis and Degradation-Aware Enhancement for Ultrasound Image Restoration](https://mlsanity.com/paper/2609.35120/) (2026)

## Abstract (arXiv)

The task of single image super-resolution (SISR) aims at reconstructing a high-resolution (HR) image from a low-resolution (LR) image. Although significant progress has been made by deep learning models, they are trained on synthetic paired data in a supervised way and do not perform well on real data. There are several attempts that directly apply unsupervised image translation models to address such a problem. However, unsupervised low-level vision problem poses more challenge on the accuracy of translation. In this work,we propose a novel framework which is composed of two stages: 1) unsupervised image translation between real LR images and synthetic LR images; 2) supervised super-resolution from approximated real LR images to HR images. It takes the synthetic LR images as a bridge and creates an indirect supervised path from real LR images to HR images. Any existed deep learning based image super-resolution model can be integrated into the second stage of the proposed framework for further improvement. In addition it shows great flexibility in balancing between distortion and perceptual quality under unsupervised setting. The proposed method is evaluated on both NTIRE 2017 and 2018 challenge datasets and achieves favorable performance against supervised methods.