mlsanityData to 7 Oct 2026

DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models

arXiv 2405.16749 ↗First posted 27 May 2024cs.LG cs.CVcited by 60

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

Abstract (arXiv)

Pretrained diffusion models (DMs) have recently been popularly used in solving inverse problems (IPs). The existing methods mostly interleave iterative steps in the reverse diffusion process and iterative steps to bring the iterates closer to satisfying the measurement constraint. However, such interleaving methods struggle to produce final results that look like natural objects of interest (i.e., manifold feasibility) and fit the measurement (i.e., measurement feasibility), especially for nonlinear IPs. Moreover, their capabilities to deal with noisy IPs with unknown types and levels of measurement noise are unknown. In this paper, we advocate viewing the reverse process in DMs as a function and propose a novel plug-in method for solving IPs using pretrained DMs, dubbed DMPlug. DMPlug addresses the issues of manifold feasibility and measurement feasibility in a principled manner, and also shows great potential for being robust to unknown types and levels of noise. Through extensive experiments across various IP tasks, including two linear and three nonlinear IPs, we demonstrate that DMPlug consistently outperforms state-of-the-art methods, often by large margins especially for nonlinear IPs. The code is available at https://github.com/sun-umn/DMPlug.

Key facts. Cited by 60 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 61 of its 80 references that are in the map. First posted on arXiv 27 May 2024.

Builds on

61 of 80 references.

Closest ancestors · 15

Same direction, newest first

  1. 2024Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction25 Mar
  2. 2023Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey18 Aug
  3. 2023Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency16 Jul
  4. 2023Accelerating Diffusion Models for Inverse Problems through Shortcut Sampling26 May
  5. 2023Denoising Diffusion Models for Plug-and-Play Image Restoration15 May
  6. 2023Implicit Diffusion Models for Continuous Super-Resolution29 Mar
  7. 2023Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration20 Mar
  8. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model1 Dec
  9. 2022EDICT: Exact Diffusion Inversion via Coupled Transformations22 Nov
  10. 2022Diffusion Model Based Posterior Sampling for Noisy Linear Inverse Problems20 Nov
  11. 2022Parallel Diffusion Models of Operator and Image for Blind Inverse Problems19 Nov
  12. 2022Diffusion Posterior Sampling for General Noisy Inverse Problems29 Sep
3 more
  1. 2022Improving Diffusion Models for Inverse Problems using Manifold Constraints2 Jun
  2. 2022Denoising Diffusion Restoration Models27 Jan
  3. 2021Deblurring via Stochastic Refinement5 Dec

Other references · 46

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  8. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  9. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  10. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  11. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  12. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
34 more
  1. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  2. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  3. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Modelscited by 1,168
  4. 2017Deep Image Priorcited by 1,097
  5. 2021Multi-Stage Progressive Image Restorationcited by 813
  6. 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 640
  7. 2021Score-based Generative Modeling in Latent Spacecited by 634
  8. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Modelscited by 634
  9. 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 411
  10. 2017DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networkscited by 366
  11. 2019DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Bettercited by 361
  12. 2016Generative Visual Manipulation on the Natural Image Manifoldcited by 348
  13. 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 290
  14. 2016Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applicationscited by 244
  15. 2020Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulationcited by 225
  16. 2022Dual Diffusion Implicit Bridges for Image-to-Image Translationcited by 212
  17. 2017Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Artcited by 182
  18. 2023Image Restoration with Mean-Reverting Stochastic Differential Equationscited by 182
  19. 2023DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statisticscited by 161
  20. 2023Manifold Preserving Guided Diffusioncited by 153
  21. 2016Inverting The Generator Of A Generative Adversarial Networkcited by 140
  22. 2022Stripformer: Strip Transformer for Fast Image Deblurringcited by 139
  23. 2021Deep Equilibrium Architectures for Inverse Problems in Imagingcited by 126
  24. 2019Neural Blind Deconvolution Using Deep Priorscited by 113
  25. 2022ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removalcited by 102
  26. 2022Deep Image Deblurring: A Surveycited by 94
  27. 2021Explore Image Deblurring via Blur Kernel Spacecited by 58
  28. 2021Early Stopping for Deep Image Priorcited by 44
  29. 2021On Measuring and Controlling the Spectral Bias of the Deep Image Priorcited by 36
  30. 2019The Spectral Bias of the Deep Image Priorcited by 20
  31. 2022Tilt-then-Blur or Blur-then-Tilt? Clarifying the Atmospheric Turbulence Modelcited by 17
  32. 2021Self-Validation: Early Stopping for Single-Instance Deep Generative Priorscited by 15
  33. 2023Kernel Diffusion: An Alternate Approach to Blind Deconvolutioncited by 13
  34. 2022Blind Image Deblurring with Unknown Kernel Size and Substantial Noisecited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 23; 2026: 29.

60 papers.

Sort:

By area:

  1. 2024A Survey on Diffusion Models for Inverse Problemscited by 173
  2. 2025Physics-Constrained Flow Matching: Sampling Generative Models with Hard Constraintscited by 46
  3. 2024Gradient-Free Generation for Hard-Constrained Systemscited by 35
  4. 2024SITCOM: Step-wise Triple-Consistent Diffusion Sampling for Inverse Problemscited by 23
  5. 2025Variational Control for Guidance in Diffusion Modelscited by 22
  6. 2024Free Hunch: Denoiser Covariance Estimation for Diffusion Models Without Extra Costscited by 14
  7. 2024Inverse Problems with Diffusion Models: A MAP Estimation Perspectivecited by 9
  8. 2025Integrating Intermediate Layer Optimization and Projected Gradient Descent for Solving Inverse Problems with Diffusion Modelscited by 7
  9. 2025A Baseline Method for Removing Invisible Image Watermarks using Deep Image Priorcited by 6
  10. 2025Whitened Score Diffusion: A Structured Prior for Imaging Inverse Problemscited by 6
  11. 2026D-Flow SGLD: Source-Space Posterior Sampling for Scientific Inverse Problems with Flow Matchingcited by 5
  12. 2025Improving Diffusion-based Inverse Algorithms under Few-Step Constraint via Learnable Linear Extrapolationcited by 4
38 more
  1. 2025Temporal-Consistent Video Restoration with Pre-trained Diffusion Modelscited by 4
  2. 2026Weak Diffusion Priors Can Still Achieve Strong Inverse-Problem Performancecited by 4
  3. 2026Provable diffusion-based posterior sampling for linear inverse problems via DDIMcited by 4
  4. 2025Dual Ascent Diffusion for Inverse Problemscited by 3
  5. 2025FMPlug: Plug-In Foundation Flow-Matching Priors for Inverse Problemscited by 3
  6. 2026Physics-informed diffusion models in spectral spacecited by 3
  7. 2026DM4CT: Benchmarking Diffusion Models for Computed Tomography Reconstructioncited by 3
  8. 2025Multitask Learning with Stochastic Interpolantscited by 2
  9. 2025Local MAP Sampling for Diffusion Modelscited by 2
  10. 2025Coupled Data and Measurement Space Dynamics for Enhanced Diffusion Posterior Samplingcited by 2
  11. 2025Latent Refinement via Flow Matching for Training-free Linear Inverse Problem Solvingcited by 2
  12. 2025Solving Diffusion Inverse Problems with Restart Posterior Samplingcited by 2
  13. 2026Conditional flow matching for physics-constrained inverse problems with finite training datacited by 2
  14. 2026Noise-Adaptive Diffusion Sampling for Inverse Problems Without Task-Specific Tuningcited by 2
  15. 2026Couple to Control: Joint Initial Noise Design in Diffusion Modelscited by 2
  16. 2026Image Restoration via Diffusion Models with Dynamic Resolutioncited by 2
  17. 2026Decoupled Latent Optimization of Diffusion Models for Full Waveform Inversioncited by 2
  18. 2024Linearly Constrained Diffusion Implicit Modelscited by 1
  19. 2024Enhancing and Accelerating Diffusion-Based Inverse Problem Solving through Measurements Optimizationcited by 1
  20. 2025Measurement-Aligned Sampling for Inverse Problemcited by 1
  21. 2025Contrastive Diffusion Guidance for Spatial Inverse Problemscited by 1
  22. 2025Inverse problems with diffusion models: MAP estimation via mode-seeking losscited by 1
  23. 2026Solving Inverse Problems with Flow-based Models via Model Predictive Controlcited by 1
  24. 2026Trajectory Stitching for Solving Inverse Problems with Flow-Based Modelscited by 1
  25. 2026FAST-DIPS: Adjoint-Free Analytic Steps and Hard-Constrained Likelihood Correction for Diffusion-Prior Inverse Problemscited by 1
  26. 2026Tunable Latent Generative Priors for Compressed Sensing and Inverse Problemscited by 1
  27. 2026Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play Frameworkcited by 1
  28. 2026Preconditioned One-Step Generative Modeling for Bayesian Inverse Problems in Function Spacescited by 1
  29. 2026Outlier-Robust Diffusion Solvers for Inverse Problemscited by 1
  30. 2026A Stability Benchmark of Generative Regularizers for Inverse Problemscited by 1
  31. 2024Improving Decoupled Posterior Sampling for Inverse Problems using Data Consistency Constraintcited by 0
  32. 2025RELD: Regularization by Latent Diffusion Models for Image Restorationcited by 0
  33. 2025LatentINDIGO: An INN-Guided Latent Diffusion Algorithm for Image Restorationcited by 0
  34. 2025Learned Regularization for Microwave Tomographycited by 0
  35. 2025cryoSENSE: Compressive Sensing Enables High-throughput Microscopy with Sparse and Generative Priors on the Protein Cryo-EM Image Manifoldcited by 0
  36. 2025Saving Foundation Flow-Matching Priors for Inverse Problemscited by 0
  37. 2025SURE Guided Posterior Sampling: Trajectory Correction for Diffusion-Based Inverse Problemscited by 0
  38. 2026A Diffusion-Based Generative Prior Approach to Sparse-view Computed Tomographycited by 0

50 most cited of 60 All 60 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Diffusion models for inverse problems
  2. 2023Direct Diffusion Bridge using Data Consistency for Inverse Problems
  3. 2025Unifying and extending Diffusion Models through PDEs for solving Inverse Problems
  4. 2025ReGuidance: A Simple Diffusion Wrapper for Boosting Sample Quality on Hard Inverse Problems
  5. 2025Solving Inverse Problems using Diffusion with Iterative Colored Renoising
  6. 2025EquiReg: Equivariance Regularized Diffusion for Inverse Problems
  7. 2025Injecting Measurement Information Yields a Fast and Noise-Robust Diffusion-Based Inverse Problem Solver
  8. 2025Noise is All You Need: Solving Linear Inverse Problems by Noise Combination Sampling with Diffusion Models