# Learning Many-to-Many Mapping for Unpaired Real-World Image Super-resolution and Downscaling

arXiv: https://arxiv.org/abs/2310.04964 · HTML: https://mlsanity.com/paper/2310.04964/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 58 of its 86 references that are in the map.
- First posted on arXiv 8 Oct 2023.

## Builds on (most cited first, 30 of 58)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Normalizing Flows for Probabilistic Modeling and Inference](https://mlsanity.com/paper/1912.02762/) (2019)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [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)
- [Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model](https://mlsanity.com/paper/1904.00523/) (2019)
- [Deep Learning for Image Super-resolution: A Survey](https://mlsanity.com/paper/1902.06068/) (2019)
- ["Zero-Shot" Super-Resolution using Deep Internal Learning](https://mlsanity.com/paper/1712.06087/) (2017)
- [Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design](https://mlsanity.com/paper/1902.00275/) (2019)
- [Component Divide-and-Conquer for Real-World Image Super-Resolution](https://mlsanity.com/paper/2008.01928/) (2020)
- [Analyzing Inverse Problems with Invertible Neural Networks](https://mlsanity.com/paper/1808.04730/) (2018)
- [SRFlow: Learning the Super-Resolution Space with Normalizing Flow](https://mlsanity.com/paper/2006.14200/) (2020)
- [PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration](https://mlsanity.com/paper/2007.12142/) (2020)
- [Blind Super-Resolution Kernel Estimation using an Internal-GAN](https://mlsanity.com/paper/1909.06581/) (2019)
- [Deep Learning for Single Image Super-Resolution: A Brief Review](https://mlsanity.com/paper/1808.03344/) (2018)
- [Learning a No-Reference Quality Metric for Single-Image Super-Resolution](https://mlsanity.com/paper/1612.05890/) (2016)
- [Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networks](https://mlsanity.com/paper/1809.00437/) (2018)
- [Unfolding the Alternating Optimization for Blind Super Resolution](https://mlsanity.com/paper/2010.02631/) (2020)
- [Dual Aggregation Transformer for Image Super-Resolution](https://mlsanity.com/paper/2308.03364/) (2023)
- [Frequency Separation for Real-World Super-Resolution](https://mlsanity.com/paper/1911.07850/) (2019)
- [Noise Flow: Noise Modeling with Conditional Normalizing Flows](https://mlsanity.com/paper/1908.08453/) (2019)

## Built on by (most cited first, 7 of 7)

- [Learning Arbitrary-Scale RAW Image Downscaling with Wavelet-based Recurrent Reconstruction](https://mlsanity.com/paper/2507.23219/) (2025)
- [Unsupervised Image Super-Resolution Reconstruction Based on Real-World Degradation Patterns](https://mlsanity.com/paper/2506.17027/) (2025)
- [Tackling Ill-posedness of Reversible Image Conversion with Well-posed Invertible Network](https://mlsanity.com/paper/2508.02111/) (2025)
- [Unsupervised Real-World Super-Resolution via Rectified Flow Degradation Modelling](https://mlsanity.com/paper/2508.07214/) (2025)
- [QuantSR+: Pushing the Limit of Quantized Image Super-Resolution Networks](https://mlsanity.com/paper/2605.22351/) (2026)
- [Efficient Remote Sensing Instance Segmentation with Linear-Time State Space Distilled Visual Foundation Models](https://mlsanity.com/paper/2606.25324/) (2026)
- [MOSAIC: Multi-Scale Object-Centric Slot Adaptation with Image-Guided Prototype Conditioning for Remote Sensing Image Super-Resolution](https://mlsanity.com/paper/2610.13547/) (2026)

## Abstract (arXiv)

Learning based single image super-resolution (SISR) for real-world images has been an active research topic yet a challenging task, due to the lack of paired low-resolution (LR) and high-resolution (HR) training images. Most of the existing unsupervised real-world SISR methods adopt a two-stage training strategy by synthesizing realistic LR images from their HR counterparts first, then training the super-resolution (SR) models in a supervised manner. However, the training of image degradation and SR models in this strategy are separate, ignoring the inherent mutual dependency between downscaling and its inverse upscaling process. Additionally, the ill-posed nature of image degradation is not fully considered. In this paper, we propose an image downscaling and SR model dubbed as SDFlow, which simultaneously learns a bidirectional many-to-many mapping between real-world LR and HR images unsupervisedly. The main idea of SDFlow is to decouple image content and degradation information in the latent space, where content information distribution of LR and HR images is matched in a common latent space. Degradation information of the LR images and the high-frequency information of the HR images are fitted to an easy-to-sample conditional distribution. Experimental results on real-world image SR datasets indicate that SDFlow can generate diverse realistic LR and SR images both quantitatively and qualitatively.