mlsanityData to 7 Oct 2026

ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting

arXiv 2307.12348 ↗First posted 23 Jul 2023cs.CVcited by 360

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

Abstract (arXiv)

Diffusion-based image super-resolution (SR) methods are mainly limited by the low inference speed due to the requirements of hundreds or even thousands of sampling steps. Existing acceleration sampling techniques inevitably sacrifice performance to some extent, leading to over-blurry SR results. To address this issue, we propose a novel and efficient diffusion model for SR that significantly reduces the number of diffusion steps, thereby eliminating the need for post-acceleration during inference and its associated performance deterioration. Our method constructs a Markov chain that transfers between the high-resolution image and the low-resolution image by shifting the residual between them, substantially improving the transition efficiency. Additionally, an elaborate noise schedule is developed to flexibly control the shifting speed and the noise strength during the diffusion process. Extensive experiments demonstrate that the proposed method obtains superior or at least comparable performance to current state-of-the-art methods on both synthetic and real-world datasets, even only with 15 sampling steps. Our code and model are available at https://github.com/zsyOAOA/ResShift.

Key facts. Cited by 360 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 59 of its 70 references that are in the map. First posted on arXiv 23 Jul 2023.

Builds on

59 of 70 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolution11 May
  2. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration20 Mar
  3. 2022DifFace: Blind Face Restoration with Diffused Error Contraction13 Dec
  4. 2022Denoising Diffusion Restoration Models27 Jan
  5. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction9 Dec
  6. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models30 Apr

Other references · 53

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  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. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  11. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  12. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
38 more
  1. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  2. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  3. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  4. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  5. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  6. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,544
  7. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  8. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  9. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,352
  10. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  11. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  12. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  13. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,199
  14. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,058
  15. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 974
  16. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  17. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 924
  18. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 634
  19. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
  20. 2017The Perception-Distortion Tradeoffcited by 582
  21. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  22. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 509
  23. 2017Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolutioncited by 452
  24. 2019Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Modelcited by 400
  25. 2015Sketch-based Manga Retrieval using Manga109 Datasetcited by 326
  26. 2020Permutation Invariant Graph Generation via Score-Based Generative Modelingcited by 263
  27. 2020Deep Unfolding Network for Image Super-Resolutioncited by 253
  28. 2020Learning Gradient Fields for Shape Generationcited by 245
  29. 2017Learning a Single Convolutional Super-Resolution Network for Multiple Degradationscited by 227
  30. 2020Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulationcited by 225
  31. 2018Deep Back-Projection Networks For Super-Resolutioncited by 224
  32. 2023I2SB: Image-to-Image Schr"odinger Bridgecited by 214
  33. 2023Image Restoration with Mean-Reverting Stochastic Differential Equationscited by 182
  34. 2020GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolutioncited by 158
  35. 2017DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networkscited by 156
  36. 2019Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernelscited by 112
  37. 2022Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolutioncited by 96
  38. 2021Flow-based Kernel Prior with Application to Blind Super-Resolutioncited by 74

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 17; 2024: 92; 2025: 146; 2026: 105.

360 papers.

Sort:

By area:

  1. 2023SeeSR: Towards Semantics-Aware Real-World Image Super-Resolutioncited by 311
  2. 2023Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylizationcited by 251
  3. 2024One-Step Effective Diffusion Network for Real-World Image Super-Resolutioncited by 243
  4. 2023SinSR: Diffusion-Based Image Super-Resolution in a Single Stepcited by 235
  5. 2023Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolutioncited by 131
  6. 2025Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noisecited by 114
  7. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Surveycited by 108
  8. 2024Pixel-level and Semantic-level Adjustable Super-resolution: A Dual-LoRA Approachcited by 93
  9. 2024Arbitrary-steps Image Super-resolution via Diffusion Inversioncited by 85
  10. 2024TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolutioncited by 83
  11. 2024Diffusion Models in Low-Level Vision: A Surveycited by 73
  12. 2023Residual Denoising Diffusion Modelscited by 68
38 more
  1. 2024AddSR: Accelerating Diffusion-based Blind Super-Resolution with Adversarial Diffusion Distillationcited by 66
  2. 2024Efficient Diffusion Model for Image Restoration by Residual Shiftingcited by 64
  3. 2024Degradation-Guided One-Step Image Super-Resolution with Diffusion Priorscited by 64
  4. 2024DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curationcited by 64
  5. 2024Diffusion Models, Image Super-Resolution And Everything: A Surveycited by 63
  6. 2025SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restorationcited by 62
  7. 2023ZONE: Zero-Shot Instruction-Guided Local Editingcited by 61
  8. 2024A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trendscited by 58
  9. 2025STAR: Spatial-Temporal Augmentation with Text-to-Video Models for Real-World Video Super-Resolutioncited by 56
  10. 2025DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolutioncited by 50
  11. 2024Adversarial Diffusion Compression for Real-World Image Super-Resolutioncited by 49
  12. 2025SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Trainingcited by 45
  13. 2023Boosting Latent Diffusion with Flow Matchingcited by 44
  14. 2025One Diffusion Step to Real-World Super-Resolution via Flow Trajectory Distillationcited by 40
  15. 2024Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolutioncited by 36
  16. 2025Efficient Diffusion Models: A Surveycited by 35
  17. 2025Harnessing Diffusion-Yielded Score Priors for Image Restorationcited by 34
  18. 2024DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration Modelscited by 33
  19. 2024Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficientcited by 32
  20. 2024FaithDiff: Unleashing Diffusion Priors for Faithful Image Super-resolutioncited by 31
  21. 2025Region-Adaptive Sampling for Diffusion Transformerscited by 31
  22. 2025DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolutioncited by 30
  23. 2024Conditional Image Synthesis with Diffusion Models: A Surveycited by 29
  24. 2025Uncertainty-guided Perturbation for Image Super-Resolution Diffusion Modelcited by 29
  25. 2024Wavelet Diffusion Neural Operatorcited by 28
  26. 2024Diffusion Models Meet Remote Sensing: Principles, Methods, and Perspectivescited by 27
  27. 2024QMambaBSR: Burst Image Super-Resolution with Query State Space Modelcited by 27
  28. 2023CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image Generationcited by 26
  29. 2024SRGS: Super-Resolution 3D Gaussian Splattingcited by 26
  30. 2025Visual-Instructed Degradation Diffusion for All-in-One Image Restorationcited by 26
  31. 2024Unveiling Hidden Details: A RAW Data-Enhanced Paradigm for Real-World Super-Resolutioncited by 25
  32. 2025S2Gaussian: Sparse-View Super-Resolution 3D Gaussian Splattingcited by 24
  33. 2024SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditionscited by 23
  34. 2024AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoisingcited by 22
  35. 2024OFTSR: One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offscited by 22
  36. 2025Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compressioncited by 22
  37. 2024RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusioncited by 21
  38. 2024Lodge++: High-quality and Long Dance Generation with Vivid Choreography Patternscited by 21

50 most cited of 360 All 360 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023ACDMSR: Accelerated Conditional Diffusion Models for Single Image Super-Resolution
  2. 2023Solving Diffusion ODEs with Optimal Boundary Conditions for Better Image Super-Resolution
  3. 2024SAM-DiffSR: Structure-Modulated Diffusion Model for Image Super-Resolution
  4. 2023ResDiff: Combining CNN and Diffusion Model for Image Super-Resolution
  5. 2025PGP-DiffSR: Phase-Guided Progressive Pruning for Efficient Diffusion-based Image Super-Resolution
  6. 2023Waving Goodbye to Low-Res: A Diffusion-Wavelet Approach for Image Super-Resolution
  7. 2026Uncertainty-Guided Latent Diffusion Models for Faithful Super Resolution
  8. 2025Diffusion Posterior Sampling for Super-Resolution under Gaussian Measurement Noise