mlsanityData to 7 Oct 2026

Exploiting Diffusion Prior for Real-World Image Super-Resolution

arXiv 2305.07015 ↗First posted 11 May 2023cs.CVcited by 486

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

Abstract (arXiv)

We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution (SR). Specifically, by employing our time-aware encoder, we can achieve promising restoration results without altering the pre-trained synthesis model, thereby preserving the generative prior and minimizing training cost. To remedy the loss of fidelity caused by the inherent stochasticity of diffusion models, we employ a controllable feature wrapping module that allows users to balance quality and fidelity by simply adjusting a scalar value during the inference process. Moreover, we develop a progressive aggregation sampling strategy to overcome the fixed-size constraints of pre-trained diffusion models, enabling adaptation to resolutions of any size. A comprehensive evaluation of our method using both synthetic and real-world benchmarks demonstrates its superiority over current state-of-the-art approaches. Code and models are available at https://github.com/IceClear/StableSR.

Key facts. Cited by 486 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 82 of its 109 references that are in the map. First posted on arXiv 11 May 2023.

Builds on

82 of 109 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023Denoising Diffusion Probabilistic Models for Robust Image Super-Resolution in the Wild15 Feb
  2. 2022DifFace: Blind Face Restoration with Diffused Error Contraction13 Dec
  3. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model1 Dec
  4. 2022Diffusion Model Based Posterior Sampling for Noisy Linear Inverse Problems20 Nov
  5. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraints2 Jun
  6. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models30 Apr

Other references · 76

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  7. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  8. 2020Denoising Diffusion Implicit Modelscited by 9,655
  9. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  10. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  11. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  12. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
38 more
  1. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  3. 2022Classifier-Free Diffusion Guidancecited by 5,717
  4. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  5. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  6. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  7. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  8. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  9. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,320
  10. 2019Searching for MobileNetV3cited by 1,984
  11. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  12. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  13. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  14. 2023Consistency Modelscited by 1,778
  15. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  16. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,339
  17. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  18. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  19. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  20. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  21. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  22. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
  23. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  24. 2022Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generationcited by 958
  25. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 924
  26. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 921
  27. 2020Pre-Trained Image Processing Transformercited by 891
  28. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesiscited by 773
  29. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 634
  30. 2017The Perception-Distortion Tradeoffcited by 582
  31. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  32. 2023FateZero: Fusing Attentions for Zero-shot Text-based Video Editingcited by 462
  33. 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 400
  34. 2016Accelerating the Super-Resolution Convolutional Neural Networkcited by 393
  35. 2022Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesiscited by 386
  36. 2018Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transformcited by 369
  37. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
  38. 2021Towards Real-World Blind Face Restoration with Generative Facial Priorcited by 347

50 most cited of 76 All 76 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 44; 2024: 135; 2025: 185; 2026: 122.

486 papers.

Sort:

By area:

  1. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shiftingcited by 360
  2. 2023LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Modelscited by 349
  3. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 311
  4. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 281
  5. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Priorcited by 255
  6. 2023Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylizationcited by 251
  7. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolutioncited by 243
  8. 2024StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generationcited by 240
  9. 2024Diffusion Model-Based Image Editing: A Surveycited by 212
  10. 2023Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolutioncited by 131
  11. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  12. 2023Controlling Vision-Language Models for Multi-Task Image Restorationcited by 108
38 more
  1. 20243DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priorscited by 106
  2. 2023DemoFusion: Democratising High-Resolution Image Generation With No cited by 105
  3. 2023AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusioncited by 98
  4. 2024Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approachcited by 93
  5. 2024VmambaIR: Visual State Space Model for Image Restorationcited by 90
  6. 2024Arbitrary-steps Image Super-resolution via Diffusion Inversioncited by 85
  7. 2024TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolutioncited by 83
  8. 2024Diffusion Models in Low-Level Vision: A Surveycited by 73
  9. 2023Prompt-tuning latent diffusion models for inverse problemscited by 70
  10. 2023CoSeR: Bridging Image and Language for Cognitive Super-Resolutioncited by 66
  11. 2024AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillationcited by 66
  12. 2024Efficient Diffusion Model for Image Restoration by Residual Shiftingcited by 64
  13. 2024UltraPixel: Advancing Ultra-High-Resolution Image Synthesis to New Peakscited by 64
  14. 2024DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curationcited by 64
  15. 2024Diffusion Models, Image Super-Resolution And Everything: A Surveycited by 63
  16. 2025SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restorationcited by 62
  17. 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 59
  18. 2023Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolutioncited by 59
  19. 2024A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trendscited by 58
  20. 2025STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolutioncited by 56
  21. 2024Meta 3D TextureGen: Fast and Consistent Texture Generation for 3D Objectscited by 52
  22. 2023Multimodal Prompt Perceiver: Empower Adaptiveness, Generalizability and Fidelity for All-in-One Image Restorationcited by 50
  23. 2025DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolutioncited by 50
  24. 2023PGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidancecited by 49
  25. 2024Adversarial Diffusion Compression for Real-World Image Super-Resolutioncited by 49
  26. 2024Diff-Plugin: Revitalizing Details for Diffusion-based Low-level Taskscited by 47
  27. 2023Neural Degradation Representation Learning for All-In-One Image Restorationcited by 46
  28. 2025SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Trainingcited by 45
  29. 2023Boosting Latent Diffusion with Flow Matchingcited by 44
  30. 2024XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolutioncited by 41
  31. 2024RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Modelscited by 41
  32. 2025One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillationcited by 40
  33. 2025UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Priorcited by 39
  34. 2023ElasticDiffusion: Training-free Arbitrary Size Image Generation through Global-Local Content Separationcited by 37
  35. 20243D MedDiffusion: A 3D Medical Latent Diffusion Model for Controllable and High-quality Medical Image Generationcited by 37
  36. 2023Any-Size-Diffusion: Toward Efficient Text-Driven Synthesis for Any-Size HD Imagescited by 36
  37. 2023Improving Image Restoration through Removing Degradations in Textual Representationscited by 36
  38. 2024Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolutioncited by 36

50 most cited of 486 All 486 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors
  2. 2026Perceptually Regularized Diffusion Model for Image Super-Resolution
  3. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Step
  4. 2023DREAM: Diffusion Rectification and Estimation-Adaptive Models
  5. 2024BlindDiff: Empowering Degradation Modelling in Diffusion Models for Blind Image Super-Resolution
  6. 2023ACDMSR: Accelerated Conditional Diffusion Models for Single Image Super-Resolution
  7. 2023Implicit Diffusion Models for Continuous Super-Resolution
  8. 2026DNF-SR: Dual-Input and Negative-Aware Feature Fine-Tuning for Real-World Image Super-Resolution