mlsanityData to 7 Oct 2026

Image Super-Resolution via Iterative Refinement

arXiv 2104.07636 ↗First posted 15 Apr 2021eess.IV cs.CV cs.LGcited by 1,506

Not on the map. Why?

Cited by 992 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present SR3, an approach to image Super-Resolution via Repeated Refinement. SR3 adapts denoising diffusion probabilistic models to conditional image generation and performs super-resolution through a stochastic denoising process. Inference starts with pure Gaussian noise and iteratively refines the noisy output using a U-Net model trained on denoising at various noise levels. SR3 exhibits strong performance on super-resolution tasks at different magnification factors, on faces and natural images. We conduct human evaluation on a standard 8X face super-resolution task on CelebA-HQ, comparing with SOTA GAN methods. SR3 achieves a fool rate close to 50%, suggesting photo-realistic outputs, while GANs do not exceed a fool rate of 34%. We further show the effectiveness of SR3 in cascaded image generation, where generative models are chained with super-resolution models, yielding a competitive FID score of 11.3 on ImageNet.

Key facts. Cited by 1,506 papers in the map (data through 7 Oct 2026). Builds on 57 of its 74 references that are in the map. First posted on arXiv 15 Apr 2021.

Builds on

57 of 74 references.

References · 57

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  7. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  8. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  9. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  10. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  11. 2013Auto-Encoding Variational Bayescited by 3,980
  12. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
38 more
  1. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  2. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  3. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  4. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  5. 2017Improved Training of Wasserstein GANscited by 2,223
  6. 2015Variational Inference with Normalizing Flowscited by 2,161
  7. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  8. 2016Density estimation using Real NVPcited by 2,029
  9. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  10. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  11. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  12. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  13. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  14. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  15. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  16. 2016Colorful Image Colorizationcited by 1,113
  17. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  18. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  19. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  20. 2016Pixel Recurrent Neural Networkscited by 814
  21. 2018Image Transformercited by 770
  22. 2017Wasserstein GANcited by 635
  23. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  24. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  25. 2017PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modificationscited by 415
  26. 2016Accelerating the Super-Resolution Convolutional Neural Networkcited by 393
  27. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
  28. 2015Deeply-Recursive Convolutional Network for Image Super-Resolutioncited by 317
  29. 2020Learning Gradient Fields for Shape Generationcited by 245
  30. 2016Generating Images with Perceptual Similarity Metrics based on Deep Networkscited by 221
  31. 2015Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networkscited by 214
  32. 2020SRFlow: Learning the Super-Resolution Space with Normalizing Flowcited by 209
  33. 2016Unrolled Generative Adversarial Networkscited by 208
  34. 2016EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesiscited by 177
  35. 2017FSRNet: End-to-End Learning Face Super-Resolution with Facial Priorscited by 170
  36. 2019Classification Accuracy Score for Conditional Generative Modelscited by 134
  37. 2020Blind Face Restoration via Deep Multi-scale Component Dictionariescited by 106
  38. 2020Solving Linear Inverse Problems Using the Prior Implicit in a Denoisercited by 78

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 33; 2022: 155; 2023: 435; 2024: 410; 2025: 300; 2026: 173.

1,506 papers.

Sort:

By area:

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  3. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  4. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  5. 2022Flow Matching for Generative Modelingcited by 5,426
  6. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  7. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  8. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  9. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  10. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  11. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  12. 2022Video Diffusion Modelscited by 2,280
38 more
  1. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  2. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  3. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  4. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,172
  5. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
  6. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  7. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,010
  8. 2022Diffusion Models in Vision: A Surveycited by 1,008
  9. 2022Denoising Diffusion Restoration Modelscited by 951
  10. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 921
  11. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesiscited by 773
  12. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 695
  13. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 694
  14. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 634
  15. 2021Diffusion Schr"odinger Bridge with Applications to Score-Based Generative Modelingcited by 594
  16. 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Modelscited by 592
  17. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Modelcited by 574
  18. 2022Executing your Commands via Motion Diffusion in Latent Spacecited by 567
  19. 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generationcited by 529
  20. 2021Label-Efficient Semantic Segmentation with Diffusion Modelscited by 495
  21. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  22. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  23. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 486
  24. 2022MagicVideo: Efficient Video Generation With Latent Diffusion Modelscited by 463
  25. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representationcited by 447
  26. 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 373
  27. 2022Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioningcited by 362
  28. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shiftingcited by 360
  29. 2023LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Modelscited by 349
  30. 2023DeepCache: Accelerating Diffusion Models for Freecited by 346
  31. 2023AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretrainingcited by 343
  32. 2023Denoising Diffusion Models for Plug-and-Play Image Restorationcited by 335
  33. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Modelscited by 331
  34. 2023VideoFusion: Decomposed Diffusion Models for High-Quality Video Generationcited by 330
  35. 2023Synthetic Data from Diffusion Models Improves ImageNet Classificationcited by 326
  36. 2022Is synthetic data from generative models ready for image recognition?cited by 320
  37. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 311
  38. 2021Score-based diffusion models for accelerated MRIcited by 308

50 most cited of 1,506 All 1,506 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models
  2. 2026Noise-Started One-Step Real-World Super-Resolution via LR-Conditioned SplitMeanFlow and GAN Refinement
  3. 2026TEASR: Training-Efficient Any-Step Diffusion Transformer for Real-World Image Super-Resolution
  4. 2026Bridging Restoration and Generation in One-step Diffusion for Real-World Image Super-Resolution
  5. 2025AdaptSR: Low-Rank Adaptation for Efficient and Scalable Real-World Super-Resolution
  6. 2025TinySR: Pruning Diffusion for Real-World Image Super-Resolution
  7. 2024Towards Realistic Data Generation for Real-World Super-Resolution
  8. 2024RAP-SR: RestorAtion Prior Enhancement in Diffusion Models for Realistic Image Super-Resolution