mlsanityData to 14 Oct 2026

Block Coordinate Plug-and-Play Methods for Blind Inverse Problems

arXiv 2305.12672 ↗First posted 22 May 2023eess.IV cs.CV cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Plug-and-play (PnP) prior is a well-known class of methods for solving imaging inverse problems by computing fixed-points of operators combining physical measurement models and learned image denoisers. While PnP methods have been extensively used for image recovery with known measurement operators, there is little work on PnP for solving blind inverse problems. We address this gap by presenting a new block-coordinate PnP (BC-PnP) method that efficiently solves this joint estimation problem by introducing learned denoisers as priors on both the unknown image and the unknown measurement operator. We present a new convergence theory for BC-PnP compatible with blind inverse problems by considering nonconvex data-fidelity terms and expansive denoisers. Our theory analyzes the convergence of BC-PnP to a stationary point of an implicit function associated with an approximate minimum mean-squared error (MMSE) denoiser. We numerically validate our method on two blind inverse problems: automatic coil sensitivity estimation in magnetic resonance imaging (MRI) and blind image deblurring. Our results show that BC-PnP provides an efficient and principled framework for using denoisers as PnP priors for jointly estimating measurement operators and images.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 53 of its 88 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

53 of 88 references.

References · 53

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2017Deep Image Priorcited by 1,098
  4. 2020Plug-and-Play Image Restoration with Deep Denoiser Priorcited by 470
  5. 2016Deep Convolutional Neural Network for Inverse Problems in Imagingcited by 433
  6. 2019Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processingcited by 421
  7. 2017Learning Deep CNN Denoiser Prior for Image Restorationcited by 408
  8. 2019DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Bettercited by 362
  9. 2016The Little Engine that Could: Regularization by Denoising (RED)cited by 307
  10. 2020Deep Learning Techniques for Inverse Problems in Imagingcited by 291
  11. 2020Deep Unfolding Network for Image Super-Resolutioncited by 254
  12. 2016Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applicationscited by 246
38 more
  1. 2017Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)cited by 224
  2. 2015Coordinate Descent Algorithmscited by 219
  3. 2020End-to-End Variational Networks for Accelerated MRI Reconstructioncited by 202
  4. 2019Plug-and-Play Methods Provably Converge with Properly Trained Denoiserscited by 198
  5. 2021Deep Equilibrium Architectures for Inverse Problems in Imagingcited by 127
  6. 2019Neural Blind Deconvolution Using Deep Priorscited by 113
  7. 2022Parallel Diffusion Models of Operator and Image for Blind Inverse Problemscited by 113
  8. 2019Deep Plug-and-Play Super-Resolution for Arbitrary Blur Kernelscited by 112
  9. 2021Gradient Step Denoiser for convergent Plug-and-Playcited by 108
  10. 2017Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problemscited by 107
  11. 2018Regularization by Denoising: Clarifications and New Interpretationscited by 103
  12. 2021Bayesian imaging using Plug & Play priors: when Langevin meets Tweediecited by 97
  13. 2017Framing U-Net via Deep Convolutional Framelets: Application to Sparse-view CTcited by 88
  14. 2016A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstructioncited by 87
  15. 2017A Review of Convolutional Neural Networks for Inverse Problems in Imagingcited by 81
  16. 2018Denoising Prior Driven Deep Neural Network for Image Restorationcited by 80
  17. 2022Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex Regularizationcited by 80
  18. 2015Plug-and-Play Priors for Bright Field Electron Tomography and Sparse Interpolationcited by 78
  19. 2019Plug and play methods for magnetic resonance imaging (long version)cited by 75
  20. 2018An Online Plug-and-Play Algorithm for Regularized Image Reconstructioncited by 70
  21. 2017Plug-and-Play Unplugged: Optimization Free Reconstruction using Consensus Equilibriumcited by 58
  22. 2020Regularization by Denoising via Fixed-Point Projection (RED-PRO)cited by 55
  23. 2020Scalable Plug-and-Play ADMM with Convergence Guaranteescited by 50
  24. 2021Recovery of Continuous 3D Refractive Index Maps from Discrete Intensity-Only Measurements using Neural Fieldscited by 48
  25. 2018prDeep: Robust Phase Retrieval with a Flexible Deep Networkcited by 47
  26. 2017Model based learning for accelerated, limited-view 3D photoacoustic tomographycited by 45
  27. 2018Blind Image Deconvolution using Deep Generative Priorscited by 40
  28. 2020Provable Convergence of Plug-and-Play Priors with MMSE denoiserscited by 39
  29. 2020Tuning-free Plug-and-Play Proximal Algorithm for Inverse Imaging Problemscited by 38
  30. 2014Incremental Majorization-Minimization Optimization with Application to Large-Scale Machine Learningcited by 35
  31. 2019Block Coordinate Regularization by Denoisingcited by 33
  32. 2020Deep Phase Decoder: Self-calibrating phase microscopy with an untrained deep neural networkcited by 24
  33. 2021Recovery Analysis for Plug-and-Play Priors using the Restricted Eigenvalue Conditioncited by 22
  34. 2022Online Deep Equilibrium Learning for Regularization by Denoisingcited by 22
  35. 2021Deep J-Sense: Accelerated MRI Reconstruction via Unrolled Alternating Optimizationcited by 19
  36. 2022SPICER: Self-Supervised Learning for MRI with Automatic Coil Sensitivity Estimation and Reconstructioncited by 10
  37. 2018On bayesian estimation and proximity operatorscited by 6
  38. 2020Joint Reconstruction and Calibration using Regularization by Denoisingcited by 5

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 3; 2025: 2; 2026: 1.

8 papers.

  1. 2023Training-free Linear Image Inverses via Flowscited by 72
  2. 2023Prior Mismatch and Adaptation in PnP-ADMM with a Nonconvex Convergence Analysiscited by 11
  3. 2024CryoFM: A Flow-based Foundation Model for Cryo-EM Densitiescited by 4
  4. 2024LoFi: Neural Local Fields for Scalable Image Reconstructioncited by 2
  5. 2025Plug-and-Play Posterior Sampling for Blind Inverse Problemscited by 2
  6. 2024ADOBI: Adaptive Diffusion Bridge For Blind Inverse Problems with Application to MRI Reconstructioncited by 1
  7. 2025Comprehensive Examination of Unrolled Networks for Solving Linear Inverse Problemscited by 1
  8. 2026A Unified Framework for Multimodal Image Reconstruction and Synthesis using Denoising Diffusion Modelscited by 1