mlsanityData to 7 Oct 2026

A Survey on Diffusion Models for Inverse Problems

arXiv 2410.00083 ↗First posted 30 Sep 2024cs.LG cs.AI cs.CVcited by 173

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

Abstract (arXiv)

Diffusion models have become increasingly popular for generative modeling due to their ability to generate high-quality samples. This has unlocked exciting new possibilities for solving inverse problems, especially in image restoration and reconstruction, by treating diffusion models as unsupervised priors. This survey provides a comprehensive overview of methods that utilize pre-trained diffusion models to solve inverse problems without requiring further training. We introduce taxonomies to categorize these methods based on both the problems they address and the techniques they employ. We analyze the connections between different approaches, offering insights into their practical implementation and highlighting important considerations. We further discuss specific challenges and potential solutions associated with using latent diffusion models for inverse problems. This work aims to be a valuable resource for those interested in learning about the intersection of diffusion models and inverse problems.

Key facts. Cited by 173 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 108 of its 163 references that are in the map. First posted on arXiv 30 Sep 2024.

Builds on

108 of 163 references.

Closest ancestors · 29

Same direction, newest first

  1. 2024Integrating Amortized Inference with Diffusion Models for Learning Clean Distribution from Corrupted Images15 Jul
  2. 2024Deep Diffusion Image Prior for Efficient OOD Adaptation in 3D Inverse Problems15 Jul
  3. 2024An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations1 Jul
  4. 2024Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors29 May
  5. 2024DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models27 May
  6. 2024Learning Diffusion Priors from Observations by Expectation Maximization22 May
  7. 2024Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Data13 Mar
  8. 2024Diffusion Posterior Sampling is Computationally Intractable20 Feb
  9. 2024Consistency Model is an Effective Posterior Sample Approximation for Diffusion Inverse Solvers9 Feb
  10. 2023Beyond First-Order Tweedie: Solving Inverse Problems using Latent Diffusion1 Dec
  11. 2023Regularization by Texts for Latent Diffusion Inverse Solvers27 Nov
  12. 2023Prompt-tuning latent diffusion models for inverse problems2 Oct
17 more
  1. 2023Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency16 Jul
  2. 2023Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models2 Jul
  3. 2023Denoising Diffusion Models for Plug-and-Play Image Restoration15 May
  4. 2023A Variational Perspective on Solving Inverse Problems with Diffusion Models7 May
  5. 2023Solving Inverse Problems with Score-Based Generative Priors learned from Noisy Data2 May
  6. 2023Score-Based Diffusion Models as Principled Priors for Inverse Imaging23 Apr
  7. 2023Refusion: Enabling Large-Size Realistic Image Restoration with Latent-Space Diffusion Models17 Apr
  8. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration20 Mar
  9. 2023Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems10 Mar
  10. 2023GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration30 Jan
  11. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model1 Dec
  12. 2022Parallel Diffusion Models of Operator and Image for Blind Inverse Problems19 Nov
  13. 2022Diffusion Posterior Sampling for General Noisy Inverse Problems29 Sep
  14. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraints2 Jun
  15. 2022Denoising Diffusion Restoration Models27 Jan
  16. 2021Deblurring via Stochastic Refinement5 Dec
  17. 2021SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models30 Apr

Other references · 79

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  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. 2022Classifier-Free Diffusion Guidancecited by 5,717
  8. 2022Flow Matching for Generative Modelingcited by 5,426
  9. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  10. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  11. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  12. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
38 more
  1. 2015Variational Inference with Normalizing Flowscited by 2,161
  2. 2016Density estimation using Real NVPcited by 2,029
  3. 2023Consistency Modelscited by 1,778
  4. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  5. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  6. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  7. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  8. 2021Palette: Image-to-Image Diffusion Modelscited by 1,296
  9. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
  10. 2022Building Normalizing Flows with Stochastic Interpolantscited by 964
  11. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 897
  12. 2021Multi-Stage Progressive Image Restorationcited by 813
  13. 2022Simple Baselines for Image Restorationcited by 701
  14. 2021Maximum Likelihood Training of Score-Based Diffusion Modelscited by 670
  15. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 634
  16. 2017The Perception-Distortion Tradeoffcited by 582
  17. 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 526
  18. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 514
  19. 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 464
  20. 2018Learning to See in the Darkcited by 459
  21. 2023Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusioncited by 448
  22. 2017DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networkscited by 366
  23. 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 359
  24. 2017Compressed Sensing using Generative Modelscited by 337
  25. 2018Scale-recurrent Network for Deep Image Deblurringcited by 332
  26. 2021Score-based diffusion models for accelerated MRIcited by 308
  27. 2016The Little Engine that Could: Regularization by Denoising (RED)cited by 303
  28. 2022MAXIM: Multi-Axis MLP for Image Processingcited by 301
  29. 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 290
  30. 2021Robust Compressed Sensing MRI with Deep Generative Priorscited by 284
  31. 2019Noise2Self: Blind Denoising by Self-Supervisioncited by 274
  32. 2016Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applicationscited by 244
  33. 2023Inpaint Anything: Segment Anything Meets Image Inpaintingcited by 233
  34. 2022Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problemcited by 229
  35. 2023Practical and Asymptotically Exact Conditional Sampling in Diffusion Modelscited by 218
  36. 2023I2SB: Image-to-Image Schr"odinger Bridgecited by 214
  37. 2021SNIPS: Solving Noisy Inverse Problems Stochasticallycited by 191
  38. 2023Image Restoration with Mean-Reverting Stochastic Differential Equationscited by 182

50 most cited of 79 All 79 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 14; 2025: 94; 2026: 65.

173 papers.

Sort:

By area:

  1. 2024Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusioncited by 47
  2. 2024Steering Rectified Flow Models in the Vector Field for Controlled Image Generationcited by 38
  3. 2025Efficient Diffusion Models: A Surveycited by 35
  4. 2024SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesiscited by 34
  5. 2025Guided Diffusion Sampling on Function Spaces with Applications to PDEscited by 33
  6. 2024Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restorationcited by 32
  7. 2025Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modelingcited by 25
  8. 2024SITCOM: Step-wise Triple-Consistent Diffusion Sampling for Inverse Problemscited by 23
  9. 2024Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Modelscited by 21
  10. 2025Split Gibbs Discrete Diffusion Posterior Samplingcited by 18
  11. 2025Solving Inverse Problems via Diffusion-Based Priors: An Approximation-Free Ensemble Sampling Approachcited by 18
  12. 2025Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilationcited by 17
38 more
  1. 2025Diffusion models for inverse problemscited by 15
  2. 2024Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra Costscited by 14
  3. 2025SteerX: Creating Any Camera-Free 3D and 4D Scenes with Geometric Steeringcited by 13
  4. 2024Frequency-Guided Posterior Sampling for Diffusion-Based Image Restorationcited by 10
  5. 2024Bayesian Experimental Design via Contrastive Diffusionscited by 9
  6. 2026Decoupled Diffusion Sampling for Inverse Problems on Function Spacescited by 9
  7. 2025Multiscale guidance of protein structure prediction with heterogeneous cryo-EM datacited by 8
  8. 2025Diffusion Models in Simulation-Based Inference: A Tutorial Reviewcited by 8
  9. 2025Inverse Problem Sampling in Latent Space Using Sequential Monte Carlocited by 7
  10. 2025Unifying and extending Diffusion Models through PDEs for solving Inverse Problemscited by 7
  11. 2025MRI Super-Resolution with Deep Learning: A Comprehensive Surveycited by 7
  12. 2024Constrained Posterior Sampling: Time Series Generation with Hard Constraintscited by 6
  13. 2024FiRe: Fixed-points of Restoration Priors for Solving Inverse Problemscited by 6
  14. 2025CKMDiff: A Generative Diffusion Model for CKM Construction via Inverse Problems with Learned Priorscited by 6
  15. 2025Whitened Score Diffusion: A Structured Prior for Imaging Inverse Problemscited by 6
  16. 2025ESS-Flow: Training-free guidance of flow-based models as inference in source spacecited by 6
  17. 2025DiffEM: Learning from Corrupted Data with Diffusion Models via Expectation Maximizationcited by 6
  18. 2025Good Things Come in Pairs: Paired Autoencoders for Inverse Problemscited by 5
  19. 2025ReGuidance: A Simple Diffusion Wrapper for Boosting Sample Quality on Hard Inverse Problemscited by 5
  20. 2025Learning few-step posterior samplers by unfolding and distillation of diffusion modelscited by 5
  21. 2025Efficient Zero-Shot Inpainting with Decoupled Diffusion Guidancecited by 5
  22. 2026How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidancecited by 5
  23. 2025Benchmarking Self-Supervised Learning Methods for Accelerated MRI Reconstructioncited by 4
  24. 2025Unsupervised Detection of Distribution Shift in Inverse Problems using Diffusion Modelscited by 4
  25. 2025Generative diffusion posterior sampling for informative likelihoodscited by 4
  26. 2025System-Embedded Diffusion Bridge Modelscited by 4
  27. 2025EigenScore: OOD Detection using Covariance in Diffusion Modelscited by 4
  28. 2025SONIC: Spectral Optimization of Noise for Inpainting with Consistencycited by 4
  29. 2026Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Roboticscited by 4
  30. 2026Provable diffusion-based posterior sampling for linear inverse problems via DDIMcited by 4
  31. 2025Diff-Unfolding: A Model-Based Score Learning Framework for Inverse Problemscited by 3
  32. 2025UGoDIT: Unsupervised Group Deep Image Prior Via Transferable Weightscited by 3
  33. 2025Dual Ascent Diffusion for Inverse Problemscited by 3
  34. 2025Repurposing Marigold for Zero-Shot Metric Depth Estimation via Defocus Blur Cuescited by 3
  35. 2025FMPlug: Plug-In Foundation Flow-Matching Priors for Inverse Problemscited by 3
  36. 2025Efficient Approximate Posterior Sampling with Annealed Langevin Monte Carlocited by 3
  37. 2025A Recovery Theory for Diffusion Priors: Deterministic Analysis of the Implicit Prior Algorithmcited by 3
  38. 2025NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problemscited by 3

50 most cited of 173 All 173 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2023Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision
  2. 2024Gaussian is All You Need: A Unified Framework for Solving Inverse Problems via Diffusion Posterior Sampling
  3. 2024G2D2: Gradient-Guided Discrete Diffusion for Inverse Problem Solving
  4. 2025SILO: Solving Inverse Problems with Latent Operators
  5. 2024Inverse Problems with Diffusion Models: A MAP Estimation Perspective
  6. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction
  7. 2024Blind Inversion using Latent Diffusion Priors
  8. 2023Removing Structured Noise with Diffusion Models