# ESRGAN+ : Further Improving Enhanced Super-Resolution Generative Adversarial Network

arXiv: https://arxiv.org/abs/2001.08073 · HTML: https://mlsanity.com/paper/2001.08073/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jan 2020.

## Built on by (most cited first, 27 of 27)

- [Fast and Explicit Neural View Synthesis](https://mlsanity.com/paper/2107.05775/) (2021)
- [Noise Conditional Flow Model for Learning the Super-Resolution Space](https://mlsanity.com/paper/2106.04428/) (2021)
- [Variational AutoEncoder for Reference based Image Super-Resolution](https://mlsanity.com/paper/2106.04090/) (2021)
- [Training Generative Image Super-Resolution Models by Wavelet-Domain Losses Enables Better Control of Artifacts](https://mlsanity.com/paper/2402.19215/) (2024)
- [Generative Adversarial Networks for Image Super-Resolution: A Survey](https://mlsanity.com/paper/2204.13620/) (2022)
- [FS-NCSR: Increasing Diversity of the Super-Resolution Space via Frequency Separation and Noise-Conditioned Normalizing Flow](https://mlsanity.com/paper/2204.09679/) (2022)
- [Capturing Climatic Variability: Using Deep Learning for Stochastic Downscaling](https://mlsanity.com/paper/2406.02587/) (2024)
- [Debiased Subjective Assessment of Real-World Image Enhancement](https://mlsanity.com/paper/2106.10080/) (2021)
- [Dual Perceptual Loss for Single Image Super-Resolution Using ESRGAN](https://mlsanity.com/paper/2201.06383/) (2022)
- [Does Diffusion Beat GAN in Image Super Resolution?](https://mlsanity.com/paper/2405.17261/) (2024)
- [Perception-Distortion Trade-off in the SR Space Spanned by Flow Models](https://mlsanity.com/paper/2209.08564/) (2022)
- [GANalyzer: Analysis and Manipulation of GANs Latent Space for Controllable Face Synthesis](https://mlsanity.com/paper/2302.00908/) (2023)
- [StarSRGAN: Improving Real-World Blind Super-Resolution](https://mlsanity.com/paper/2307.16169/) (2023)
- [Leveraging Vision-Language Models to Select Trustworthy Super-Resolution Samples Generated by Diffusion Models](https://mlsanity.com/paper/2506.20832/) (2025)
- [AGA-GAN: Attribute Guided Attention Generative Adversarial Network with U-Net for Face Hallucination](https://mlsanity.com/paper/2111.10591/) (2021)
- [Exploiting Digital Surface Models for Inferring Super-Resolution for Remotely Sensed Images](https://mlsanity.com/paper/2205.04056/) (2022)
- [Trustworthy SR: Resolving Ambiguity in Image Super-resolution via Diffusion Models and Human Feedback](https://mlsanity.com/paper/2402.07597/) (2024)
- [Fortifying Fully Convolutional Generative Adversarial Networks for Image Super-Resolution Using Divergence Measures](https://mlsanity.com/paper/2404.06294/) (2024)
- [Deep Learning based Optical Image Super-Resolution via Generative Diffusion Models for Layerwise in-situ LPBF Monitoring](https://mlsanity.com/paper/2409.13171/) (2024)
- [Binarization-Aware Adjuster for Discrete Decision Learning with an Application to Edge Detection](https://mlsanity.com/paper/2506.12460/) (2025)
- [ATP-Net: An Attention-based Ternary Projection Network For Compressed Sensing](https://mlsanity.com/paper/2106.12728/) (2021)
- [Adaptive adversarial training method for improving multi-scale GAN based on generalization bound theory](https://mlsanity.com/paper/2211.16791/) (2022)
- [An Empirical Study of Super-resolution on Low-resolution Micro-expression Recognition](https://mlsanity.com/paper/2310.10022/) (2023)
- [Learning-Based and Quality Preserving Super-Resolution of Noisy Images](https://mlsanity.com/paper/2311.02254/) (2023)
- [ML-CrAIST: Multi-scale Low-high Frequency Information-based Cross black Attention with Image Super-resolving Transformer](https://mlsanity.com/paper/2408.09940/) (2024)
- [Involution and BSConv Multi-Depth Distillation Network for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2503.14779/) (2025)
- [SupResDiffGAN a new approach for the Super-Resolution task](https://mlsanity.com/paper/2504.13622/) (2025)

## Abstract (arXiv)

Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) is a perceptual-driven approach for single image super resolution that is able to produce photorealistic images. Despite the visual quality of these generated images, there is still room for improvement. In this fashion, the model is extended to further improve the perceptual quality of the images. We have designed a novel block to replace the one used by the original ESRGAN. Moreover, we introduce noise inputs to the generator network in order to exploit stochastic variation. The resulting images present more realistic textures. The code is available at https://github.com/ncarraz/ESRGANplus .