mlsanityData to 7 Oct 2026

Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data

arXiv 2107.10833 ↗First posted 22 Jul 2021eess.IV cs.CVcited by 961

Not on the map. Why?

Cited by 327 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Though many attempts have been made in blind super-resolution to restore low-resolution images with unknown and complex degradations, they are still far from addressing general real-world degraded images. In this work, we extend the powerful ESRGAN to a practical restoration application (namely, Real-ESRGAN), which is trained with pure synthetic data. Specifically, a high-order degradation modeling process is introduced to better simulate complex real-world degradations. We also consider the common ringing and overshoot artifacts in the synthesis process. In addition, we employ a U-Net discriminator with spectral normalization to increase discriminator capability and stabilize the training dynamics. Extensive comparisons have shown its superior visual performance than prior works on various real datasets. We also provide efficient implementations to synthesize training pairs on the fly.

Key facts. Cited by 961 papers in the map (data through 7 Oct 2026). Builds on 37 of its 55 references that are in the map. First posted on arXiv 22 Jul 2021.

Builds on

37 of 55 references.

References · 37

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,678
  4. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  5. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  6. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  7. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  8. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  9. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,199
  10. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,063
  11. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  12. 2018Residual Dense Network for Image Super-Resolutioncited by 796
25 more
  1. 2017The Perception-Distortion Tradeoffcited by 582
  2. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  3. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 452
  4. 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 400
  5. 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 369
  6. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 347
  7. 2015Deeply-Recursive Convolutional Network for Image Super-Resolutioncited by 317
  8. 2020Component Divide-and-Conquer for Real-World Image Super-Resolutioncited by 243
  9. 2018Deep Back-Projection Networks For Super-Resolutioncited by 224
  10. 2019Blind Super-Resolution With Iterative Kernel Correctioncited by 203
  11. 2016EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesiscited by 177
  12. 2021Unsupervised Degradation Representation Learning for Blind Super-Resolutioncited by 177
  13. 2019Blind Super-Resolution Kernel Estimation using an Internal-GANcited by 175
  14. 2018Non-Local Recurrent Network for Image Restorationcited by 160
  15. 2020GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolutioncited by 158
  16. 2017DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networkscited by 156
  17. 2018The 2018 PIRM Challenge on Perceptual Image Super-resolutioncited by 155
  18. 2018Unsupervised Image Super-Resolution using Cycle-in-Cycle Generative Adversarial Networkscited by 133
  19. 2020Unfolding the Alternating Optimization for Blind Super Resolutioncited by 129
  20. 2020A U-Net Based Discriminator for Generative Adversarial Networkscited by 128
  21. 2019Frequency Separation for Real-World Super-Resolutioncited by 115
  22. 2021Blind Image Super-Resolution: A Survey and Beyondcited by 93
  23. 2019Unsupervised Learning for Real-World Super-Resolutioncited by 64
  24. 2019Path-Restore: Learning Network Path Selection for Image Restorationcited by 39
  25. 2019Fine-grained Attention and Feature-sharing Generative Adversarial Networks for Single Image Super-Resolutioncited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 83; 2023: 151; 2024: 207; 2025: 288; 2026: 218.

961 papers.

Sort:

By area:

  1. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  2. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 921
  3. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  4. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 486
  5. 2024CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assetscited by 444
  6. 2022Activating More Pixels in Image Super-Resolution Transformercited by 433
  7. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shiftingcited by 360
  8. 2024MambaIR: A Simple Baseline for Image Restoration with State-Space Modelcited by 349
  9. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 311
  10. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 301
  11. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 281
  12. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Priorcited by 255
38 more
  1. 2023DiffIR: Efficient Diffusion Model for Image Restorationcited by 253
  2. 2023Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylizationcited by 251
  3. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolutioncited by 243
  4. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Stepcited by 235
  5. 2023Generative Diffusion Prior for Unified Image Restoration and Enhancementcited by 198
  6. 2023Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generationcited by 153
  7. 2023RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Pathscited by 141
  8. 2022KNN-Diffusion: Image Generation via Large-Scale Retrievalcited by 135
  9. 2021Investigating Tradeoffs in Real-World Video Super-Resolutioncited by 133
  10. 2024Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Imagecited by 132
  11. 2023Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolutioncited by 131
  12. 2023Consistent View Synthesis with Pose-Guided Diffusion Modelscited by 117
  13. 2022Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolutioncited by 114
  14. 2024Improving Diffusion Models for Authentic Virtual Try-on in the Wildcited by 109
  15. 2023CoDeF: Content Deformation Fields for Temporally Consistent Video Processingcited by 108
  16. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  17. 2023Controlling Vision-Language Models for Multi-Task Image Restorationcited by 108
  18. 2025One-Minute Video Generation with Test-Time Trainingcited by 100
  19. 2022Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priorscited by 98
  20. 2023AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusioncited by 98
  21. 2022Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolutioncited by 96
  22. 2022LEDNet: Joint Low-light Enhancement and Deblurring in the Darkcited by 95
  23. 2025Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Controlcited by 95
  24. 2024Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approachcited by 93
  25. 2024VmambaIR: Visual State Space Model for Image Restorationcited by 90
  26. 2023ARNIQA: Learning Distortion Manifold for Image Quality Assessmentcited by 87
  27. 2022Practical Blind Image Denoising via Swin-Conv-UNet and Data Synthesiscited by 85
  28. 2024Arbitrary-steps Image Super-resolution via Diffusion Inversioncited by 85
  29. 2024TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolutioncited by 83
  30. 2022GRAM-HD: 3D-Consistent Image Generation at High Resolution with Generative Radiance Manifoldscited by 73
  31. 2023RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priorscited by 73
  32. 2022Any-resolution Training for High-resolution Image Synthesiscited by 72
  33. 2022Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restorationcited by 72
  34. 2021FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimizationcited by 71
  35. 2022Masked Frequency Modeling for Self-Supervised Visual Pre-Trainingcited by 70
  36. 2022CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolutioncited by 69
  37. 2023CoSeR: Bridging Image and Language for Cognitive Super-Resolutioncited by 66
  38. 2024AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillationcited by 66

50 most cited of 961 All 961 (JSON)