mlsanityData to 7 Oct 2026

Generative Plug and Play: Posterior Sampling for Inverse Problems

arXiv 2306.07233 ↗First posted 12 Jun 2023cs.CV eess.IVcited by 24

Not on the map. Why?

Abstract (arXiv)

Over the past decade, Plug-and-Play (PnP) has become a popular method for reconstructing images using a modular framework consisting of a forward and prior model. The great strength of PnP is that an image denoiser can be used as a prior model while the forward model can be implemented using more traditional physics-based approaches. However, a limitation of PnP is that it reconstructs only a single deterministic image. In this paper, we introduce Generative Plug-and-Play (GPnP), a generalization of PnP to sample from the posterior distribution. As with PnP, GPnP has a modular framework using a physics-based forward model and an image denoising prior model. However, in GPnP these models are extended to become proximal generators, which sample from associated distributions. GPnP applies these proximal generators in alternation to produce samples from the posterior. We present experimental simulations using the well-known BM3D denoiser. Our results demonstrate that the GPnP method is robust, easy to implement, and produces intuitively reasonable samples from the posterior for sparse interpolation and tomographic reconstruction. Code to accompany this paper is available at https://github.com/gbuzzard/generative-pnp-allerton .

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 11 of its 21 references that are in the map. First posted on arXiv 12 Jun 2023.

Builds on

11 of 21 references.

References · 11

  1. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  2. 2013Auto-Encoding Variational Bayescited by 3,980
  3. 2014Conditional Generative Adversarial Netscited by 2,152
  4. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,375
  5. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,036
  6. 2021Solving Inverse Problems in Medical Imaging with Score-Based Generative Modelscited by 514
  7. 2021Robust Compressed Sensing MRI with Deep Generative Priorscited by 284
  8. 2023Score-Based Diffusion Models as Principled Priors for Inverse Imagingcited by 126
  9. 2015Plug-and-Play Priors for Bright Field Electron Tomography and Sparse Interpolationcited by 78
  10. 2017Plug-and-Play Unplugged: Optimization Free Reconstruction using Consensus Equilibriumcited by 58
  11. 2020Multi-Slice Fusion for Sparse-View and Limited-Angle 4D CT Reconstructioncited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 6; 2025: 8; 2026: 8.

24 papers.

Sort:

By area:

  1. 2024Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstructioncited by 73
  2. 2023Provable Probabilistic Imaging using Score-Based Generative Priorscited by 51
  3. 2024Tutorial on Diffusion Models for Imaging and Visioncited by 49
  4. 2024An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observationscited by 20
  5. 2024Plug-and-Play image restoration with Stochastic deNOising REgularizationcited by 17
  6. 2023Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Modelscited by 8
  7. 2025Strictly Constrained Generative Modeling via Split Augmented Langevin Samplingcited by 6
  8. 2024Plug-and-Play Priors as a Score-Based Methodcited by 5
  9. 2025Learning Cocoercive Conservative Denoisers via Helmholtz Decomposition for Poisson Inverse Problemscited by 4
  10. 2025Blade: A Derivative-free Bayesian Inversion Method using Diffusion Priorscited by 3
  11. 2025PSI3D: Plug-and-Play 3D Stochastic Inference with Slice-wise Latent Diffusion Priorcited by 3
  12. 2026Stochastic Generative Plug-and-Play Priorscited by 3
12 more
  1. 2024Learning truly monotone operators with applications to nonlinear inverse problemscited by 2
  2. 2025Plug-and-Play Latent Diffusion for Electromagnetic Inverse Scattering with Application to Brain Imagingcited by 2
  3. 2025Solving Inverse Problems using Diffusion with Iterative Colored Renoisingcited by 1
  4. 2026Bayesian Signal Component Decomposition via Diffusion-within-Gibbs Samplingcited by 1
  5. 2026Composing diffusion priors with explicit physical context via generative Gibbs samplingcited by 1
  6. 2025Supporting renewable energy planning and operation with data-driven high-resolution ensemble weather forecastcited by 0
  7. 2025Bregman geometry-aware split Gibbs sampling for Bayesian Poisson inverse problemscited by 0
  8. 2026Diffusion Graph Posterior Sampling for Nonlinear Inverse Problems with Application to Electrical Impedance Tomographycited by 0
  9. 2026Unbiased Diffusion Variational Inversion via Principled Posterior Matchingcited by 0
  10. 2026Zeroth-Order Non-Log-Concave Sampling with Variance Reduction and Applications to Inverse Problemscited by 0
  11. 2026Bridging data-driven priors via the score function for posterior sampling -- Comparative review and experimental studycited by 0
  12. 2026FlowSGS: Improving Flow Matching Priors for Inverse Imaging with Stochastic Interpolantscited by 0