mlsanityData to 7 Oct 2026

AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillation

arXiv 2404.01717 ↗First posted 2 Apr 2024cs.CV eess.IVcited by 66

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

Abstract (arXiv)

Blind super-resolution methods based on stable diffusion showcase formidable generative capabilities in reconstructing clear high-resolution images with intricate details from low-resolution inputs. However, their practical applicability is often hampered by poor efficiency, stemming from the requirement of thousands or hundreds of sampling steps. Inspired by the efficient adversarial diffusion distillation (ADD), we design~name~to address this issue by incorporating the ideas of both distillation and ControlNet. Specifically, we first propose a prediction-based self-refinement strategy to provide high-frequency information in the student model output with marginal additional time cost. Furthermore, we refine the training process by employing HR images, rather than LR images, to regulate the teacher model, providing a more robust constraint for distillation. Second, we introduce a timestep-adaptive ADD to address the perception-distortion imbalance problem introduced by original ADD. Extensive experiments demonstrate our~name~generates better restoration results, while achieving faster speed than previous SD-based state-of-the-art models (e.g., 7× faster than SeeSR).

Key facts. Cited by 66 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 53 of its 75 references that are in the map. First posted on arXiv 2 Apr 2024.

Builds on

53 of 75 references.

Closest ancestors · 9

Same direction, newest first

  1. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution27 Nov
  2. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Step23 Nov
  3. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior29 Aug
  4. 2023Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization28 Aug
  5. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting23 Jul
  6. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolution11 May
  7. 2023DiffIR: Efficient Diffusion Model for Image Restoration16 Mar
  8. 2023Denoising Diffusion Probabilistic Models for Robust Image Super-Resolution in the Wild15 Feb
  9. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models30 Apr

Other references · 44

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  8. 2022Classifier-Free Diffusion Guidancecited by 5,717
  9. 2022Generative Adversarial Networkscited by 5,603
  10. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  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
32 more
  1. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  2. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  3. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  4. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  5. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
  6. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  7. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 924
  8. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  9. 2020Pre-Trained Image Processing Transformercited by 891
  10. 2023Adversarial Diffusion Distillationcited by 741
  11. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 695
  12. 2017The Perception-Distortion Tradeoffcited by 582
  13. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  14. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 514
  15. 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 400
  16. 2023Recognize Anything: A Strong Image Tagging Modelcited by 305
  17. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 281
  18. 2024SDXL-Lightning: Progressive Adversarial Diffusion Distillationcited by 258
  19. 2017MemNet: A Persistent Memory Network for Image Restorationcited by 244
  20. 2020Component Divide-and-Conquer for Real-World Image Super-Resolutioncited by 243
  21. 2023StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesiscited by 212
  22. 2020PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restorationcited by 177
  23. 2022Efficient Long-Range Attention Network for Image Super-resolutioncited by 151
  24. 2022Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolutioncited by 114
  25. 2022Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priorscited by 98
  26. 2022NTIRE 2022 Challenge on Perceptual Image Quality Assessmentcited by 41
  27. 2023DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Modelscited by 41
  28. 2023ArtBank: Artistic Style Transfer with Pre-trained Diffusion Model and Implicit Style Prompt Bankcited by 36
  29. 2022MM-RealSR: Metric Learning based Interactive Modulation for Real-World Super-Resolutioncited by 33
  30. 2022Knowledge Distillation based Degradation Estimation for Blind Super-Resolutioncited by 28
  31. 2024SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditionscited by 23
  32. 2022Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolutioncited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 10; 2025: 30; 2026: 26.

66 papers.

Sort:

By area:

  1. 2024TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolutioncited by 83
  2. 2025DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolutioncited by 50
  3. 2024Adversarial Diffusion Compression for Real-World Image Super-Resolutioncited by 49
  4. 2025SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Trainingcited by 45
  5. 2025One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillationcited by 40
  6. 20243DIS: Depth-Driven Decoupled Instance Synthesis for Text-to-Image Generationcited by 36
  7. 2025Harnessing Diffusion-Yielded Score Priors for Image Restorationcited by 34
  8. 2025Does FLUX Already Know How to Perform Physically Plausible Image Composition?cited by 30
  9. 2025Uncertainty-guided Perturbation for Image Super-Resolution Diffusion Modelcited by 29
  10. 2025DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editingcited by 29
  11. 2025DreamRenderer: Taming Multi-Instance Attribute Control in Large-Scale Text-to-Image Modelscited by 28
  12. 2024OFTSR: One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offscited by 22
38 more
  1. 2025From Zero to Detail: Deconstructing Ultra-High-Definition Image Restoration from Progressive Spectral Perspectivecited by 22
  2. 2025Investigating Text Insulation and Attention Mechanisms for Complex Visual Text Generationcited by 22
  3. 2024Effective Diffusion Transformer Architecture for Image Super-Resolutioncited by 20
  4. 2024Unleashing the Power of One-Step Diffusion based Image Super-Resolution via a Large-Scale Diffusion Discriminatorcited by 18
  5. 2024One Step Diffusion-based Super-Resolution with Time-Aware Distillationcited by 17
  6. 2025Consistency Trajectory Matching for One-Step Generative Super-Resolutioncited by 15
  7. 2025Dual Prompting Image Restoration with Diffusion Transformerscited by 15
  8. 2024MambaCSR: Dual-Interleaved Scanning for Compressed Image Super-Resolution With SSMscited by 14
  9. 2026LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Expertscited by 13
  10. 2025RayFlow: Instance-Aware Diffusion Acceleration via Adaptive Flow Trajectoriescited by 12
  11. 2025Acquire and then Adapt: Squeezing out Text-to-Image Model for Image Restorationcited by 8
  12. 2025PocketSR: The Super-Resolution Expert in Your Pocket Mobilescited by 8
  13. 2025TinySR: Pruning Diffusion for Real-World Image Super-Resolutioncited by 7
  14. 2026Fast Image Super-Resolution via Consistency Rectified Flowcited by 7
  15. 2025Towards All-in-One Medical Image Re-Identificationcited by 6
  16. 2026From Zero to Detail: A Progressive Spectral Decoupling Paradigm for UHD Image Restoration with New Benchmarkcited by 6
  17. 2024Hero-SR: One-Step Diffusion for Super-Resolution with Human Perception Priorscited by 5
  18. 2025GenDR: Lighten Generative Detail Restorationcited by 5
  19. 2025One-Step Diffusion-based Real-World Image Super-Resolution with Visual Perception Distillationcited by 5
  20. 2024TASR: Timestep-Aware Diffusion Model for Image Super-Resolutioncited by 4
  21. 2026Improved Adversarial Diffusion Compression for Real-World Video Super-Resolutioncited by 4
  22. 2026DUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolutioncited by 4
  23. 2025LR0.FM: Low-Res Benchmark and Improving Robustness for Zero-Shot Classification in Foundation Modelscited by 3
  24. 2025SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-Conditioningcited by 3
  25. 2025Bridging Fidelity-Reality with Controllable One-Step Diffusion for Image Super-Resolutioncited by 3
  26. 2026FiDeSR: High-Fidelity and Detail-Preserving One-Step Diffusion Super-Resolutioncited by 3
  27. 2026GDPO-SR: Group Direct Preference Optimization for One-Step Generative Image Super-Resolutioncited by 3
  28. 2025One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillationcited by 2
  29. 2025CTSR: Controllable Fidelity-Realness Trade-off Distillation for Real-World Image Super Resolutioncited by 2
  30. 2025DP2O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolutioncited by 2
  31. 2025ICM-SR: Image-Conditioned Manifold Regularization for Image Super-Resolutioncited by 2
  32. 2026SwiftVR: Real-Time One-Step Generative Video Restorationcited by 2
  33. 2025Mixture of Ranks with Degradation-Aware Routing for One-Step Real-World Image Super-Resolutioncited by 1
  34. 2026Fast, faithful and photorealistic diffusion-based image super-resolution with enhanced Flow Map modelscited by 1
  35. 2026Eliminating VAE for Fast and High-Resolution Generative Detail Restorationcited by 1
  36. 2026MFSR: MeanFlow Distillation for One Step Real-World Image Super Resolutioncited by 1
  37. 2026VARestorer: One-Step VAR Distillation for Real-World Image Super-Resolutioncited by 1
  38. 2026DreamSR: Towards Ultra-High-Resolution Image Super-Resolution via a Receptive-Field Enhanced Diffusion Transformercited by 1

50 most cited of 66 All 66 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026TEASR: Training-Efficient Any-Step Diffusion Transformer for Real-World Image Super-Resolution
  2. 2023Improving the Stability and Efficiency of Diffusion Models for Content Consistent Super-Resolution
  3. 2025EAM: Enhancing Anything with Diffusion Transformers for Blind Super-Resolution
  4. 2025Boosting Diffusion Guidance via Learning Degradation-Aware Models for Blind Super Resolution
  5. 2023DREAM: Diffusion Rectification and Estimation-Adaptive Models
  6. 2026PhoenixSR: Generative Heterogeneous Distillation Unleashes Efficient Models for Real-World Super-Resolution
  7. 2024You Only Need One Step: Fast Super-Resolution with Stable Diffusion via Scale Distillation
  8. 2023Dissecting Arbitrary-scale Super-resolution Capability from Pre-trained Diffusion Generative Models