mlsanityData to 7 Oct 2026

ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks

arXiv 1809.00219 ↗First posted 1 Sep 2018cs.CVcited by 1,250

Not on the map. Why?

Cited by 210 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

The Super-Resolution Generative Adversarial Network (SRGAN) is a seminal work that is capable of generating realistic textures during single image super-resolution. However, the hallucinated details are often accompanied with unpleasant artifacts. To further enhance the visual quality, we thoroughly study three key components of SRGAN - network architecture, adversarial loss and perceptual loss, and improve each of them to derive an Enhanced SRGAN (ESRGAN). In particular, we introduce the Residual-in-Residual Dense Block (RRDB) without batch normalization as the basic network building unit. Moreover, we borrow the idea from relativistic GAN to let the discriminator predict relative realness instead of the absolute value. Finally, we improve the perceptual loss by using the features before activation, which could provide stronger supervision for brightness consistency and texture recovery. Benefiting from these improvements, the proposed ESRGAN achieves consistently better visual quality with more realistic and natural textures than SRGAN and won the first place in the PIRM2018-SR Challenge. The code is available at https://github.com/xinntao/ESRGAN .

Key facts. Cited by 1,250 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 2; 2021: 213; 2022: 231; 2023: 257; 2024: 211; 2025: 208; 2026: 128.

1,250 papers.

Sort:

By area:

  1. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  2. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  3. 2021Transformers in Vision: A Surveycited by 1,009
  4. 2022Diffusion Models in Vision: A Surveycited by 1,008
  5. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  6. 2021Multi-Stage Progressive Image Restorationcited by 813
  7. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  8. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 514
  9. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  10. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 486
  11. 2022Activating More Pixels in Image Super-Resolution Transformercited by 433
  12. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
38 more
  1. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shiftingcited by 360
  2. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 347
  3. 2025Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generationcited by 342
  4. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 311
  5. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contractioncited by 306
  6. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 301
  7. 2021SegDiff: Image Segmentation with Diffusion Probabilistic Modelscited by 279
  8. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Priorcited by 255
  9. 2023DiffIR: Efficient Diffusion Model for Image Restorationcited by 253
  10. 2023Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylizationcited by 251
  11. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolutioncited by 243
  12. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Stepcited by 235
  13. 2023Implicit Diffusion Models for Continuous Super-Resolutioncited by 216
  14. 2023StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesiscited by 212
  15. 2021Vision Transformers are Robust Learnerscited by 208
  16. 2021SNIPS: Solving Noisy Inverse Problems Stochasticallycited by 191
  17. 2021Low-Light Image Enhancement with Normalizing Flowcited by 184
  18. 2022VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolutioncited by 174
  19. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restorationcited by 164
  20. 2022Efficient Long-Range Attention Network for Image Super-resolutioncited by 151
  21. 2022Learning Enriched Features for Fast Image Restoration and Enhancementcited by 150
  22. 2021Low-Light Image and Video Enhancement Using Deep Learning: A Surveycited by 148
  23. 2023Efficient and Explicit Modelling of Image Hierarchies for Image Restorationcited by 145
  24. 2024InstructIR: High-Quality Image Restoration Following Human Instructionscited by 139
  25. 2024Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformerscited by 137
  26. 2021Investigating Tradeoffs in Real-World Video Super-Resolutioncited by 133
  27. 2022Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolutioncited by 114
  28. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  29. 2022Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolutioncited by 96
  30. 2022LEDNet: Joint Low-light Enhancement and Deblurring in the Darkcited by 95
  31. 2021Blind Image Super-Resolution: A Survey and Beyondcited by 93
  32. 2024Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approachcited by 93
  33. 2024VmambaIR: Visual State Space Model for Image Restorationcited by 90
  34. 2021LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyondcited by 88
  35. 2023Refusion: Enabling Large-Size Realistic Image Restoration with Latent-Space Diffusion Modelscited by 86
  36. 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?cited by 84
  37. 2021Deep Burst Super-Resolutioncited by 83
  38. 2021Equivariant Imaging: Learning Beyond the Range Spacecited by 83

50 most cited of 1,250 All 1,250 (JSON)