mlsanityData to 14 Oct 2026

Fast Diffusion EM: a diffusion model for blind inverse problems with application to deconvolution

arXiv 2309.00287 ↗First posted 1 Sep 2023cs.CVcited by 36

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

Abstract (arXiv)

Using diffusion models to solve inverse problems is a growing field of research. Current methods assume the degradation to be known and provide impressive results in terms of restoration quality and diversity. In this work, we leverage the efficiency of those models to jointly estimate the restored image and unknown parameters of the degradation model such as blur kernel. In particular, we designed an algorithm based on the well-known Expectation-Minimization (EM) estimation method and diffusion models. Our method alternates between approximating the expected log-likelihood of the inverse problem using samples drawn from a diffusion model and a maximization step to estimate unknown model parameters. For the maximization step, we also introduce a novel blur kernel regularization based on a Plug & Play denoiser. Diffusion models are long to run, thus we provide a fast version of our algorithm. Extensive experiments on blind image deblurring demonstrate the effectiveness of our method when compared to other state-of-the-art approaches.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models. Builds on 32 of its 57 references that are in the map. First posted on arXiv 1 Sep 2023.

Builds on

32 of 57 references.

Closest ancestors · 4

Same direction, newest first

  1. 2022Parallel Diffusion Models of Operator and Image for Blind Inverse Problems19 Nov
  2. 2022Diffusion Posterior Sampling for General Noisy Inverse Problems29 Sep
  3. 2022Denoising Diffusion Restoration Models27 Jan
  4. 2021Deblurring via Stochastic Refinement5 Dec

Other references · 28

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  7. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  8. 2022Classifier-Free Diffusion Guidancecited by 5,847
  9. 2014Conditional Generative Adversarial Netscited by 2,162
  10. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,887
  11. 2021Image Super-Resolution via Iterative Refinementcited by 1,511
  12. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
16 more
  1. 2021Multi-Stage Progressive Image Restorationcited by 816
  2. 2017FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoisingcited by 510
  3. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 470
  4. 2020Deep Unfolding Network for Image Super-Resolutioncited by 254
  5. 2017Learning a Single Convolutional Super-Resolution Network for Multiple Degradationscited by 228
  6. 2019Plug-and-Play Methods Provably Converge with Properly Trained Denoiserscited by 198
  7. 2019Blind Super-Resolution Kernel Estimation using an Internal-GANcited by 175
  8. 2019Neural Blind Deconvolution Using Deep Priorscited by 113
  9. 2021Gradient Step Denoiser for convergent Plug-and-Playcited by 108
  10. 2021Bayesian imaging using Plug & Play priors: when Langevin meets Tweediecited by 97
  11. 2022Plug-and-Play Methods for Integrating Physical and Learned Models in Computational Imagingcited by 96
  12. 2021Flow-based Kernel Prior with Application to Blind Super-Resolutioncited by 74
  13. 2022Deep Constrained Least Squares for Blind Image Super-Resolutioncited by 47
  14. 2022Deep Model-Based Super-Resolution with Non-uniform Blurcited by 10
  15. 2023Blind Motion Deblurring with Pixel-Wise Kernel Estimation via Kernel Prediction Networkscited by 8
  16. 2017Stochastic Proximal Gradient Algorithms for Penalized Mixed Modelscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 15; 2025: 16; 2026: 2.

36 papers.

Sort:

By area:

  1. 2024Diffusion Models in Low-Level Vision: A Surveycited by 74
  2. 2023Training-free Linear Image Inverses via Flowscited by 72
  3. 2023Prompt-tuning latent diffusion models for inverse problemscited by 70
  4. 2024Blind Image Restoration via Fast Diffusion Inversioncited by 30
  5. 2025Diffusion models for inverse problemscited by 16
  6. 2024Adaptive Compressed Sensing with Diffusion-Based Posterior Samplingcited by 13
  7. 2024Unsupervised Blind Joint Dereverberation and Room Acoustics Estimation with Diffusion Modelscited by 11
  8. 2024Blind Inversion using Latent Diffusion Priorscited by 10
  9. 2024BUDDy: Single-Channel Blind Unsupervised Dereverberation with Diffusion Modelscited by 9
  10. 2025InterLCM: Low-Quality Images as Intermediate States of Latent Consistency Models for Effective Blind Face Restorationcited by 9
  11. 2025One-Step Diffusion Model for Image Motion-Deblurringcited by 9
  12. 2025ArrayDPS: Unsupervised Blind Speech Separation with a Diffusion Priorcited by 7
24 more
  1. 2024Do Bayesian imaging methods report trustworthy probabilities?cited by 6
  2. 2024Empirical Bayesian image restoration by Langevin sampling with a denoising diffusion implicit priorcited by 6
  3. 2023FLAIR: A Conditional Diffusion Framework with Applications to Face Video Restorationcited by 5
  4. 2024Listening to the Noise: Blind Denoising with Gibbs Diffusioncited by 5
  5. 2025Unsupervised Imaging Inverse Problems with Diffusion Distribution Matchingcited by 5
  6. 2024Taming Generative Diffusion Prior for Universal Blind Image Restorationcited by 4
  7. 2024CryoFM: A Flow-based Foundation Model for Cryo-EM Densitiescited by 4
  8. 2025Unsupervised Estimation of Nonlinear Audio Effects: Comparing Diffusion-Based and Adversarial approachescited by 4
  9. 2025DynFaceRestore: Balancing Fidelity and Quality in Diffusion-Guided Blind Face Restoration with Dynamic Blur-Level Mapping and Guidancecited by 2
  10. 2025Blind Strong Gravitational Lensing Inversion: Joint Inference of Source and Lens Mass with Score-Based Modelscited by 2
  11. 2024Mixed Noise and Posterior Estimation with Conditional DeepGEMcited by 1
  12. 2024Linearly Constrained Diffusion Implicit Modelscited by 1
  13. 2024Blind Inverse Problem Solving Made Easy by Text-to-Image Latent Diffusioncited by 1
  14. 2025Double Blind Imaging with Generative Modelingcited by 1
  15. 2025Position-Blind Ptychography: Viability of image reconstruction via data-driven variational inferencecited by 1
  16. 2025Let Language Constrain Geometry: Vision-Language Models as Semantic and Spatial Critics for 3D Generationcited by 1
  17. 2025On the Sample Complexity of Learning for Blind Inverse Problemscited by 1
  18. 2024Prototype Clustered Diffusion Models for Versatile Inverse Problemscited by 0
  19. 2025Learning Graph Representation of Agent Diffuserscited by 0
  20. 2025LatentINDIGO: An INN-Guided Latent Diffusion Algorithm for Image Restorationcited by 0
  21. 2025Unsupervised Multi-channel Speech Dereverberation via Diffusioncited by 0
  22. 2025Self-Diffusion Driven Blind Imagingcited by 0
  23. 2026Saturation-Aware Space-Variant Blind Image Deblurringcited by 0
  24. 2026Music Restoration via Latent Operator Optimization and Diffusion Model Priorscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Plug-and-Play Posterior Sampling for Blind Inverse Problems
  2. 2024Learning Diffusion Model from Noisy Measurement using Principled Expectation-Maximization Method
  3. 2024An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations
  4. 2023GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration
  5. 2024A Survey on Diffusion Models for Inverse Problems
  6. 2024Unleashing the Denoising Capability of Diffusion Prior for Solving Inverse Problems
  7. 2023A Variational Perspective on Solving Inverse Problems with Diffusion Models
  8. 2026Stop Denoising Your Blurs