# A-ESRGAN: Training Real-World Blind Super-Resolution with Attention U-Net Discriminators

arXiv: https://arxiv.org/abs/2112.10046 · HTML: https://mlsanity.com/paper/2112.10046/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 31 references that are in the map.
- First posted on arXiv 19 Dec 2021.

## Builds on (most cited first, 19 of 19)

- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Designing a Practical Degradation Model for Deep Blind Image Super-Resolution](https://mlsanity.com/paper/2103.14006/) (2021)
- [Plug-and-Play Image Restoration with Deep Denoiser Prior](https://mlsanity.com/paper/2008.13751/) (2020)
- [Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution](https://mlsanity.com/paper/1704.03915/) (2017)
- [Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform](https://mlsanity.com/paper/1804.02815/) (2018)
- [Deeply-Recursive Convolutional Network for Image Super-Resolution](https://mlsanity.com/paper/1511.04491/) (2015)
- [EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis](https://mlsanity.com/paper/1612.07919/) (2016)
- [A U-Net Based Discriminator for Generative Adversarial Networks](https://mlsanity.com/paper/2002.12655/) (2020)
- [Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis](https://mlsanity.com/paper/1601.04589/) (2016)
- [Attention in Attention Network for Image Super-Resolution](https://mlsanity.com/paper/2104.09497/) (2021)

## Built on by (most cited first, 6 of 6)

- [Journey into Automation: Image-Derived Pavement Texture Extraction and Evaluation](https://mlsanity.com/paper/2501.02414/) (2025)
- [StarSRGAN: Improving Real-World Blind Super-Resolution](https://mlsanity.com/paper/2307.16169/) (2023)
- [Fine-tuned Generative Adversarial Network-based Model for Medical Image Super-Resolution](https://mlsanity.com/paper/2211.00577/) (2022)
- [Underwater Image Super-Resolution using Generative Adversarial Network-based Model](https://mlsanity.com/paper/2211.03550/) (2022)
- [Using Super-Resolution Imaging for Recognition of Low-Resolution Blurred License Plates: A Comparative Study of Real-ESRGAN, A-ESRGAN, and StarSRGAN](https://mlsanity.com/paper/2403.15466/) (2024)
- [Assessing the Impact of Image Super Resolution on White Blood Cell Classification Accuracy](https://mlsanity.com/paper/2508.03759/) (2025)

## Abstract (arXiv)

Blind image super-resolution(SR) is a long-standing task in CV that aims to restore low-resolution images suffering from unknown and complex distortions. Recent work has largely focused on adopting more complicated degradation models to emulate real-world degradations. The resulting models have made breakthroughs in perceptual loss and yield perceptually convincing results. However, the limitation brought by current generative adversarial network structures is still significant: treating pixels equally leads to the ignorance of the image's structural features, and results in performance drawbacks such as twisted lines and background over-sharpening or blurring. In this paper, we present A-ESRGAN, a GAN model for blind SR tasks featuring an attention U-Net based, multi-scale discriminator that can be seamlessly integrated with other generators. To our knowledge, this is the first work to introduce attention U-Net structure as the discriminator of GAN to solve blind SR problems. And the paper also gives an interpretation for the mechanism behind multi-scale attention U-Net that brings performance breakthrough to the model. Through comparison experiments with prior works, our model presents state-of-the-art level performance on the non-reference natural image quality evaluator metric. And our ablation studies have shown that with our discriminator, the RRDB based generator can leverage the structural features of an image in multiple scales, and consequently yields more perceptually realistic high-resolution images compared to prior works.