mlsanityData to 7 Oct 2026

Equivariant Sampling for Improving Diffusion Model-based Image Restoration

arXiv 2511.09965 ↗First posted 13 Nov 2025cs.CVcited by 1

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

Abstract (arXiv)

Recent advances in generative models, especially diffusion models, have significantly improved image restoration (IR) performance. However, existing problem-agnostic diffusion model-based image restoration (DMIR) methods face challenges in fully leveraging diffusion priors, resulting in suboptimal performance. In this paper, we address the limitations of current problem-agnostic DMIR methods by analyzing their sampling process and providing effective solutions. We introduce EquS, a DMIR method that imposes equivariant information through dual sampling trajectories. To further boost EquS, we propose the Timestep-Aware Schedule (TAS) and introduce EquS^+. TAS prioritizes deterministic steps to enhance certainty and sampling efficiency. Extensive experiments on benchmarks demonstrate that our method is compatible with previous problem-agnostic DMIR methods and significantly boosts their performance without increasing computational costs. Our code is available at https://github.com/FouierL/EquS.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 87 of its 113 references that are in the map. First posted on arXiv 13 Nov 2025.

Builds on

87 of 113 references.

Closest ancestors · 24

Same direction, newest first

  1. 2024Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems23 Jul
  2. 2024Zero-Shot Adaptation for Approximate Posterior Sampling of Diffusion Models in Inverse Problems16 Jul
  3. 2024Deep Diffusion Image Prior for Efficient OOD Adaptation in 3D Inverse Problems15 Jul
  4. 2024CDFormer:When Degradation Prediction Embraces Diffusion Model for Blind Image Super-Resolution13 May
  5. 2024Building Bridges across Spatial and Temporal Resolutions: Reference-Based Super-Resolution via Change Priors and Conditional Diffusion Model26 Mar
  6. 2023Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidance27 Dec
  7. 2023Diffusion-based Blind Text Image Super-Resolution13 Dec
  8. 2023Deep Equilibrium Diffusion Restoration with Parallel Sampling20 Nov
  9. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior29 Aug
  10. 2023Residual Denoising Diffusion Models25 Aug
  11. 2023Direct Diffusion Bridge using Data Consistency for Inverse Problems31 May
  12. 2023Hierarchical Integration Diffusion Model for Realistic Image Deblurring22 May
12 more
  1. 2023Denoising Diffusion Models for Plug-and-Play Image Restoration15 May
  2. 2023Exploiting Diffusion Prior for Real-World Image Super-Resolution11 May
  3. 2023Implicit Diffusion Models for Continuous Super-Resolution29 Mar
  4. 2023DiffIR: Efficient Diffusion Model for Image Restoration16 Mar
  5. 2023Unlimited-Size Diffusion Restoration1 Mar
  6. 2022DifFace: Blind Face Restoration with Diffused Error Contraction13 Dec
  7. 2022Multiscale Structure Guided Diffusion for Image Deblurring4 Dec
  8. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model1 Dec
  9. 2022Diffusion Posterior Sampling for General Noisy Inverse Problems29 Sep
  10. 2022Denoising Diffusion Restoration Models27 Jan
  11. 2021Deblurring via Stochastic Refinement5 Dec
  12. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models30 Apr

Other references · 63

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  8. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  9. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  10. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  11. 2017Improved Training of Wasserstein GANscited by 2,223
  12. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
38 more
  1. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  2. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  3. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  4. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  5. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  6. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
  7. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  8. 2022Diffusion Models in Vision: A Surveycited by 1,008
  9. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  10. 2015Accurate Image Super-Resolution Using Very Deep Convolutional Networkscited by 902
  11. 2022Simple Baselines for Image Restorationcited by 701
  12. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 634
  13. 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
  14. 2017The Perception-Distortion Tradeoffcited by 582
  15. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 526
  16. 2021Designing a Practical Degradation Model for Deep Blind Image Super-Resolutioncited by 524
  17. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 467
  18. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 359
  19. 2020PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Modelscited by 358
  20. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 274
  21. 2020Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulationcited by 225
  22. 2022VRT: A Video Restoration Transformercited by 219
  23. 2022MAT: Mask-Aware Transformer for Large Hole Image Inpaintingcited by 216
  24. 2023I2SB: Image-to-Image Schr"odinger Bridgecited by 214
  25. 2021SNIPS: Solving Noisy Inverse Problems Stochasticallycited by 191
  26. 2022Lossy Image Compression with Conditional Diffusion Modelscited by 165
  27. 2015Compression Artifacts Reduction by a Deep Convolutional Networkcited by 136
  28. 2022Solving 3D Inverse Problems using Pre-trained 2D Diffusion Modelscited by 130
  29. 2019Noisier2Noise: Learning to Denoise from Unpaired Noisy Datacited by 125
  30. 2021Video Super-Resolution Transformercited by 120
  31. 2021Noise2Score: Tweedie's Approach to Self-Supervised Image Denoising without Clean Imagescited by 110
  32. 2021Aggregated Contextual Transformations for High-Resolution Image Inpaintingcited by 89
  33. 2021Equivariant Imaging: Learning Beyond the Range Spacecited by 83
  34. 2020DuDoRNet: Learning a Dual-Domain Recurrent Network for Fast MRI Reconstruction with Deep T1 Priorcited by 72
  35. 2022CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolutioncited by 69
  36. 2019DuDoNet: Dual Domain Network for CT Metal Artifact Reductioncited by 68
  37. 2019Image Inpainting with Learnable Bidirectional Attention Mapscited by 64
  38. 2023Zero-Shot Noise2Noise: Efficient Image Denoising without any Datacited by 59

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Ambisonics Encoding of Room Impulse Responses using a Device-Agnostic Diffusion Modelcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Diffusion Posterior Proximal Sampling for Image Restoration
  2. 2024Decoupled Data Consistency with Diffusion Purification for Image Restoration
  3. 2025EquiReg: Equivariance Regularized Diffusion for Inverse Problems
  4. 2025DGSolver: Diffusion Generalist Solver with Universal Posterior Sampling for Image Restoration
  5. 2023A Unified Conditional Framework for Diffusion-based Image Restoration
  6. 2024Fast Samplers for Inverse Problems in Iterative Refinement Models
  7. 2025Normalization-equivariant Diffusion Models: Learning Posterior Samplers From Noisy And Partial Measurements
  8. 2024Frequency-Guided Posterior Sampling for Diffusion-Based Image Restoration