mlsanityData to 7 Oct 2026

TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution

arXiv 2411.18263 ↗First posted 27 Nov 2024cs.CVcited by 83

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

Abstract (arXiv)

Pre-trained text-to-image diffusion models are increasingly applied to real-world image super-resolution (Real-ISR) task. Given the iterative refinement nature of diffusion models, most existing approaches are computationally expensive. While methods such as SinSR and OSEDiff have emerged to condense inference steps via distillation, their performance in image restoration or details recovery is not satisfied. To address this, we propose TSD-SR, a novel distillation framework specifically designed for real-world image super-resolution, aiming to construct an efficient and effective one-step model. We first introduce the Target Score Distillation, which leverages the priors of diffusion models and real image references to achieve more realistic image restoration. Secondly, we propose a Distribution-Aware Sampling Module to make detail-oriented gradients more readily accessible, addressing the challenge of recovering fine details. Extensive experiments demonstrate that our TSD-SR has superior restoration results (most of the metrics perform the best) and the fastest inference speed (e.g. 40 times faster than SeeSR) compared to the past Real-ISR approaches based on pre-trained diffusion priors.

Key facts. Cited by 83 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 55 of its 70 references that are in the map. First posted on arXiv 27 Nov 2024.

Builds on

55 of 70 references.

Closest ancestors · 10

Same direction, newest first

  1. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolution12 Jun
  2. 2024AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillation2 Apr
  3. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution27 Nov
  4. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Step23 Nov
  5. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior29 Aug
  6. 2023Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization28 Aug
  7. 2023ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting23 Jul
  8. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolution11 May
  9. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model1 Dec
  10. 2022Denoising Diffusion Restoration Models27 Jan

Other references · 45

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  8. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  9. 2022Classifier-Free Diffusion Guidancecited by 5,717
  10. 2022Generative Adversarial Networkscited by 5,603
  11. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  12. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
33 more
  1. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  2. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  3. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  4. 2014Conditional Generative Adversarial Netscited by 2,152
  5. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  6. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  7. 2020Knowledge Distillation: A Surveycited by 1,578
  8. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  9. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  10. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
  11. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  12. 2023One-step Diffusion with Distribution Matching Distillationcited by 978
  13. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
  14. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  15. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  16. 2020Pre-Trained Image Processing Transformercited by 891
  17. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 826
  18. 2020Image Quality Assessment: Unifying Structure and Texture Similaritycited by 792
  19. 2023Adversarial Diffusion Distillationcited by 741
  20. 2024Improved Distribution Matching Distillation for Fast Image Synthesiscited by 648
  21. 2017The Perception-Distortion Tradeoffcited by 582
  22. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  23. 2022MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessmentcited by 514
  24. 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 400
  25. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 281
  26. 2020Component Divide-and-Conquer for Real-World Image Super-Resolutioncited by 243
  27. 2022Efficient Long-Range Attention Network for Image Super-resolutioncited by 151
  28. 2022Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolutioncited by 114
  29. 2023SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score Distillationcited by 109
  30. 2022Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priorscited by 98
  31. 2017Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inferencecited by 97
  32. 2022Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolutioncited by 19
  33. 2022Revisiting L1 Loss in Super-Resolution: A Probabilistic View and Beyondcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 39; 2026: 43.

83 papers.

Sort:

By area:

  1. 2025DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolutioncited by 50
  2. 2025SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Trainingcited by 45
  3. 2025One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillationcited by 40
  4. 2025FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolutioncited by 40
  5. 2025DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolutioncited by 30
  6. 2025One-Step Diffusion-Based Image Compression with Semantic Distillationcited by 23
  7. 2025UniTEX: Universal High Fidelity Generative Texturing for 3D Shapescited by 23
  8. 2024OFTSR: One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offscited by 22
  9. 2026LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editingcited by 15
  10. 2025One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolutioncited by 14
  11. 2025NTIRE 2025 Challenge on Image Super-Resolution (x4): Methods and Resultscited by 12
  12. 2025NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Resultscited by 10
38 more
  1. 2026The Fourth Challenge on Image Super-Resolution (×4) at NTIRE 2026: Benchmark Results and Method Overviewcited by 10
  2. 2025InfVSR: Toward Consistency-Driven Streaming Generative Video Super-Resolutioncited by 8
  3. 2025PocketSR: The Super-Resolution Expert in Your Pocket Mobilescited by 8
  4. 2025TinySR: Pruning Diffusion for Real-World Image Super-Resolutioncited by 7
  5. 2025One-Step Diffusion Transformer for Controllable Real-World Image Super-Resolutioncited by 7
  6. 2026Fast Image Super-Resolution via Consistency Rectified Flowcited by 7
  7. 2025Time-Aware One Step Diffusion Network for Real-World Image Super-Resolutioncited by 6
  8. 2026PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusioncited by 6
  9. 2025RealSR-R1: Reinforcement Learning for Real-World Image Super-Resolution with Vision-Language Chain-of-Thoughtcited by 5
  10. 2025FideDiff: Efficient Diffusion Model for High-Fidelity Image Motion Deblurringcited by 4
  11. 2026Improved Adversarial Diffusion Compression for Real-World Video Super-Resolutioncited by 4
  12. 2026DUO-VSR: Dual-Stream Distillation for One-Step Video Super-Resolutioncited by 4
  13. 2025Bridging the Perception Gap in Image Super-Resolution Evaluationcited by 3
  14. 2025SRSR: Enhancing Semantic Accuracy in Real-World Image Super-Resolution with Spatially Re-Focused Text-Conditioningcited by 3
  15. 2025Bridging Fidelity-Reality with Controllable One-Step Diffusion for Image Super-Resolutioncited by 3
  16. 2025FinPercep-RM: A Fine-grained Reward Model and Co-evolutionary Curriculum for RL-based Real-world Super-Resolutioncited by 3
  17. 2026FiDeSR: High-Fidelity and Detail-Preserving One-Step Diffusion Super-Resolutioncited by 3
  18. 2026GDPO-SR: Group Direct Preference Optimization for One-Step Generative Image Super-Resolutioncited by 3
  19. 2025One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillationcited by 2
  20. 2025CTSR: Controllable Fidelity-Realness Trade-off Distillation for Real-World Image Super Resolutioncited by 2
  21. 2025DP2O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolutioncited by 2
  22. 2025Restore Text First, Enhance Image Later: Two-Stage Scene Text Image Super-Resolution with Glyph Structure Guidancecited by 2
  23. 2025Enhancing Diffusion-based Restoration Models via Difficulty-Adaptive Reinforcement Learning with IQA Rewardcited by 2
  24. 2025ICM-SR: Image-Conditioned Manifold Regularization for Image Super-Resolutioncited by 2
  25. 2026How far have we gone in Generative Image Restoration? A study on its capability, limitations and evaluation practicescited by 2
  26. 2026VOSR: A Vision-Only Generative Model for Image Super-Resolutioncited by 2
  27. 2026FluxFlow: Conservative Flow-Matching for Astronomical Image Super-Resolutioncited by 2
  28. 2025HonestFace: Towards Honest Face Restoration with One-Step Diffusion Modelcited by 1
  29. 2025Low-Resolution Editing is All You Need for High-Resolution Editingcited by 1
  30. 2025OmniScaleSR: Unleashing Scale-Controlled Diffusion Prior for Faithful and Realistic Arbitrary-Scale Image Super-Resolutioncited by 1
  31. 2026LSGQuant: Layer-Sensitivity Guided Quantization for One-Step Diffusion Real-World Video Super-Resolutioncited by 1
  32. 2026Bird-SR: Bidirectional Reward-Guided Diffusion for Real-World Image Super-Resolutioncited by 1
  33. 2026Spectral and Trajectory Regularization for Diffusion Transformer Super-Resolutioncited by 1
  34. 2026MFSR: MeanFlow Distillation for One Step Real-World Image Super Resolutioncited by 1
  35. 2026PASDiff: Physics-Aware Semantic Guidance for Joint Real-World Low-Light Face Enhancement and Restorationcited by 1
  36. 2026Bridging Restoration and Generation in One-step Diffusion for Real-World Image Super-Resolutioncited by 1
  37. 2026PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text 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 83 All 83 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024One Step Diffusion-based Super-Resolution with Time-Aware Distillation
  2. 2024CasSR: Activating Image Power for Real-World Image Super-Resolution
  3. 2024You Only Need One Step: Fast Super-Resolution with Stable Diffusion via Scale Distillation
  4. 2026TOC-SR: Task-Optimal Compact diffusion for Image Super Resolution
  5. 2023ACDMSR: Accelerated Conditional Diffusion Models for Single Image Super-Resolution
  6. 2025Semantic-Guided Diffusion Model for Single-Step Image Super-Resolution
  7. 2025Realism Control One-step Diffusion for Real-World Image Super-Resolution
  8. 2026PhoenixSR: Generative Heterogeneous Distillation Unleashes Efficient Models for Real-World Super-Resolution