mlsanityData to 7 Oct 2026

Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network

arXiv 1609.04802 ↗First posted 15 Sep 2016cs.CV stat.MLcited by 1,898

Not on the map. Why?

Cited by 233 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Despite the breakthroughs in accuracy and speed of single image super-resolution using faster and deeper convolutional neural networks, one central problem remains largely unsolved: how do we recover the finer texture details when we super-resolve at large upscaling factors? The behavior of optimization-based super-resolution methods is principally driven by the choice of the objective function. Recent work has largely focused on minimizing the mean squared reconstruction error. The resulting estimates have high peak signal-to-noise ratios, but they are often lacking high-frequency details and are perceptually unsatisfying in the sense that they fail to match the fidelity expected at the higher resolution. In this paper, we present SRGAN, a generative adversarial network (GAN) for image super-resolution (SR). To our knowledge, it is the first framework capable of inferring photo-realistic natural images for 4x upscaling factors. To achieve this, we propose a perceptual loss function which consists of an adversarial loss and a content loss. The adversarial loss pushes our solution to the natural image manifold using a discriminator network that is trained to differentiate between the super-resolved images and original photo-realistic images. In addition, we use a content loss motivated by perceptual similarity instead of similarity in pixel space. Our deep residual network is able to recover photo-realistic textures from heavily downsampled images on public benchmarks. An extensive mean-opinion-score (MOS) test shows hugely significant gains in perceptual quality using SRGAN. The MOS scores obtained with SRGAN are closer to those of the original high-resolution images than to those obtained with any state-of-the-art method.

Key facts. Cited by 1,898 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Sep 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 3; 2021: 449; 2022: 403; 2023: 322; 2024: 306; 2025: 263; 2026: 151.

1,898 papers.

Sort:

By area:

  1. 2022Generative Adversarial Networkscited by 5,603
  2. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  3. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  4. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  5. 2021Transformers in Vision: A Surveycited by 1,009
  6. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  7. 2022Denoising Diffusion Restoration Modelscited by 951
  8. 2021Multi-Stage Progressive Image Restorationcited by 813
  9. 2022Autoregressive Image Generation using Residual Quantizationcited by 706
  10. 2021Masked Feature Prediction for Self-Supervised Visual Pre-Trainingcited by 573
  11. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  12. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 515
38 more
  1. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  2. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 486
  3. 2022Activating More Pixels in Image Super-Resolution Transformercited by 433
  4. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Modelscited by 415
  5. 2024MambaIR: A Simple Baseline for Image Restoration with State-Space Modelcited by 349
  6. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 347
  7. 2023Denoising Diffusion Models for Plug-and-Play Image Restorationcited by 335
  8. 2021Score-based diffusion models for accelerated MRIcited by 308
  9. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contractioncited by 306
  10. 2022Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learningcited by 302
  11. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 301
  12. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Priorcited by 255
  13. 2023DiffIR: Efficient Diffusion Model for Image Restorationcited by 253
  14. 2023Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylizationcited by 251
  15. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolutioncited by 243
  16. 2021HINet: Half Instance Normalization Network for Image Restorationcited by 236
  17. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Stepcited by 235
  18. 2021GeoQA: A Geometric Question Answering Benchmark Towards Multimodal Numerical Reasoningcited by 224
  19. 2022VRT: A Video Restoration Transformercited by 219
  20. 2022MAT: Mask-Aware Transformer for Large Hole Image Inpaintingcited by 216
  21. 2023Implicit Diffusion Models for Continuous Super-Resolutioncited by 216
  22. 2023I2SB: Image-to-Image Schr"odinger Bridgecited by 214
  23. 2022The Role of ImageNet Classes in Fr'echet Inception Distancecited by 211
  24. 2021Vision Transformers are Robust Learnerscited by 208
  25. 2021DetCo: Unsupervised Contrastive Learning for Object Detectioncited by 205
  26. 2021Projected GANs Converge Fastercited by 204
  27. 2021PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformerscited by 204
  28. 2022Versatile Diffusion: Text, Images and Variations All in One Diffusion Modelcited by 199
  29. 2023Generative Diffusion Prior for Unified Image Restoration and Enhancementcited by 198
  30. 2021GAN Prior Embedded Network for Blind Face Restoration in the Wildcited by 197
  31. 2019Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Modelscited by 177
  32. 2022VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolutioncited by 174
  33. 2021StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generatorscited by 164
  34. 2022Generative Modelling With Inverse Heat Dissipationcited by 164
  35. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restorationcited by 164
  36. 2021TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Upcited by 162
  37. 2022Efficient Long-Range Attention Network for Image Super-resolutioncited by 151
  38. 2022Learning Enriched Features for Fast Image Restoration and Enhancementcited by 150

50 most cited of 1,898 All 1,898 (JSON)