mlsanityData to 7 Oct 2026

SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models

arXiv 2104.14951 ↗First posted 30 Apr 2021cs.CVcited by 415

On the map: Diffusion models → Inverse problems and image restoration

Abstract (arXiv)

Single image super-resolution (SISR) aims to reconstruct high-resolution (HR) images from the given low-resolution (LR) ones, which is an ill-posed problem because one LR image corresponds to multiple HR images. Recently, learning-based SISR methods have greatly outperformed traditional ones, while suffering from over-smoothing, mode collapse or large model footprint issues for PSNR-oriented, GAN-driven and flow-based methods respectively. To solve these problems, we propose a novel single image super-resolution diffusion probabilistic model (SRDiff), which is the first diffusion-based model for SISR. SRDiff is optimized with a variant of the variational bound on the data likelihood and can provide diverse and realistic SR predictions by gradually transforming the Gaussian noise into a super-resolution (SR) image conditioned on an LR input through a Markov chain. In addition, we introduce residual prediction to the whole framework to speed up convergence. Our extensive experiments on facial and general benchmarks (CelebA and DIV2K datasets) show that 1) SRDiff can generate diverse SR results in rich details with state-of-the-art performance, given only one LR input; 2) SRDiff is easy to train with a small footprint; and 3) SRDiff can perform flexible image manipulation including latent space interpolation and content fusion.

Key facts. Cited by 415 papers in the map (data through 7 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 38 of its 67 references that are in the map. First posted on arXiv 30 Apr 2021.

Builds on

38 of 67 references.

References · 38

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  6. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  7. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  8. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  9. 2016Improved Techniques for Training GANscited by 2,938
  10. 2016Density estimation using Real NVPcited by 2,029
  11. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  12. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
26 more
  1. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  2. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  3. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  4. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  5. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  6. 2014NICE: Non-linear Independent Components Estimationcited by 1,052
  7. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  8. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  9. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  10. 2015Deeply-Recursive Convolutional Network for Image Super-Resolutioncited by 317
  11. 2015Deep multi-scale video prediction beyond mean square errorcited by 297
  12. 2020SRFlow: Learning the Super-Resolution Space with Normalizing Flowcited by 209
  13. 2016EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesiscited by 177
  14. 2021Symbolic Music Generation with Diffusion Modelscited by 152
  15. 2019RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolutioncited by 145
  16. 2019Mish: A Self Regularized Non-Monotonic Activation Functioncited by 141
  17. 2019Mode Seeking Generative Adversarial Networks for Diverse Image Synthesiscited by 138
  18. 2020Closed-loop Matters: Dual Regression Networks for Single Image Super-Resolutioncited by 90
  19. 2019Diversity-Sensitive Conditional Generative Adversarial Networkscited by 77
  20. 2019Progressive Face Super-Resolution via Attention to Facial Landmarkcited by 73
  21. 2019SROBB: Targeted Perceptual Loss for Single Image Super-Resolutioncited by 31
  22. 2020DeepSEE: Deep Disentangled Semantic Explorative Extreme Super-Resolutioncited by 17
  23. 2019Adaptive Density Estimation for Generative Modelscited by 16
  24. 2018Generative adversarial network-based image super-resolution using perceptual content lossescited by 8
  25. 2019Bayesian Inference with Generative Adversarial Network Priorscited by 6
  26. 2019Generative Collaborative Networks for Single Image Super-Resolutioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 11; 2022: 38; 2023: 121; 2024: 116; 2025: 84; 2026: 45.

415 papers.

Sort:

By area:

  1. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  2. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  3. 2021Label-Efficient Semantic Segmentation with Diffusion Modelscited by 495
  4. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolutioncited by 486
  5. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representationcited by 447
  6. 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 373
  7. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shiftingcited by 360
  8. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  9. 2023DeepCache: Accelerating Diffusion Models for Freecited by 346
  10. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Modelscited by 331
  11. 2023VideoFusion: Decomposed Diffusion Models for High-Quality Video Generationcited by 330
  12. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contractioncited by 306
38 more
  1. 2021SegDiff: Image Segmentation with Diffusion Probabilistic Modelscited by 279
  2. 2022Diffusion Models for Medical Image Analysis: A Comprehensive Surveycited by 269
  3. 2023Q-Diffusion: Quantizing Diffusion Modelscited by 266
  4. 2023DiffIR: Efficient Diffusion Model for Image Restorationcited by 253
  5. 2021Deblurring via Stochastic Refinementcited by 248
  6. 2022A Survey on Generative Diffusion Modelcited by 238
  7. 2021Score-Based Generative Modeling with Critically-Damped Langevin Diffusioncited by 230
  8. 2023Guided Motion Diffusion for Controllable Human Motion Synthesiscited by 221
  9. 2023Implicit Diffusion Models for Continuous Super-Resolutioncited by 216
  10. 2024Diffusion Model-Based Image Editing: A Surveycited by 212
  11. 2021SNIPS: Solving Noisy Inverse Problems Stochasticallycited by 191
  12. 2023Image Restoration with Mean-Reverting Stochastic Differential Equationscited by 182
  13. 2024A Survey on Diffusion Models for Inverse Problemscited by 173
  14. 2021On Fast Sampling of Diffusion Probabilistic Modelscited by 170
  15. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restorationcited by 164
  16. 2022A Physics-informed Diffusion Model for High-fidelity Flow Field Reconstructioncited by 150
  17. 2022Semantic Image Synthesis via Diffusion Modelscited by 131
  18. 2021Learning to Efficiently Sample from Diffusion Probabilistic Modelscited by 129
  19. 2022GENIE: Higher-Order Denoising Diffusion Solverscited by 127
  20. 2022Score-Based Generative Models Detect Manifoldscited by 121
  21. 2022Differentially Private Diffusion Modelscited by 118
  22. 2023Consistent View Synthesis with Pose-Guided Diffusion Modelscited by 117
  23. 2023TRACT: Denoising Diffusion Models with Transitive Closure Time-Distillationcited by 115
  24. 2023VidToMe: Video Token Merging for Zero-Shot Video Editingcited by 111
  25. 2023SyncDiffusion: Coherent Montage via Synchronized Joint Diffusionscited by 108
  26. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  27. 2023Optimizing Diffusion Noise Can Serve As Universal Motion Priorscited by 97
  28. 2022DifFace: Blind Face Restoration with Diffused Error Contractioncited by 96
  29. 2022Exploring Chemical Space with Score-based Out-of-distribution Generationcited by 95
  30. 2023LDMVFI: Video Frame Interpolation with Latent Diffusion Modelscited by 88
  31. 2023Hierarchical Integration Diffusion Model for Realistic Image Deblurringcited by 87
  32. 2023TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Modelscited by 86
  33. 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?cited by 84
  34. 2022Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Modelscited by 83
  35. 2022Multiscale Structure Guided Diffusion for Image Deblurringcited by 76
  36. 2024An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimizationcited by 72
  37. 20233D-aware Image Generation using 2D Diffusion Modelscited by 69
  38. 2024Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Modelscited by 68

50 most cited of 415 All 415 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Step
  2. 2021Image Super-Resolution via Iterative Refinement
  3. 2024TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution
  4. 2026TOC-SR: Task-Optimal Compact diffusion for Image Super Resolution
  5. 2024Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors
  6. 2024FaithDiff: Unleashing Diffusion Priors for Faithful Image Super-resolution
  7. 2025Semantic-Guided Diffusion Model for Single-Step Image Super-Resolution
  8. 2025TinySR: Pruning Diffusion for Real-World Image Super-Resolution