Score-Based Turbo Message Passing for Plug-and-Play Compressive Image Recovery
On the map: Diffusion models → Inverse problems and image restoration
Abstract (arXiv)
Message passing algorithms have been tailored for compressive imaging applications by plugging in different types of off-the-shelf image denoisers. These off-the-shelf denoisers mostly rely on some generic or hand-crafted priors for denoising. Due to their insufficient accuracy in capturing the true image prior, these methods often fail to produce satisfactory results, especially in highly underdetermined scenarios. On the other hand, score-based generative modeling offers a promising way to accurately characterize the sophisticated image distribution. In this paper, by exploiting the close relation between score-based modeling and empirical Bayes-optimal denoising, we devise a message passing framework that integrates a score-based minimum mean squared error (MMSE) denoiser for compressive image recovery. Experiments on the FFHQ dataset demonstrate that our method strikes a significantly better performance-complexity tradeoff than conventional message passing, regularized linear regression, and score-based posterior sampling baselines. Remarkably, our method typically converges in fewer than 20 neural function evaluations (NFEs).
Key facts. Cited by 2 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 17 of its 39 references that are in the map. First posted on arXiv 28 Mar 2025.
Builds on
17 of 39 references.
Closest ancestors · 5
Same direction, newest first
- 2024A Survey on Diffusion Models for Inverse Problems30 Sep
- 2023Denoising Diffusion Models for Plug-and-Play Image Restoration15 May
- 2022Diffusion Posterior Sampling for General Noisy Inverse Problems29 Sep
- 2022Improving Diffusion Models for Inverse Problems using Manifold Constraints2 Jun
- 2022Denoising Diffusion Restoration Models27 Jan
Other references · 12
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
- 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
- 2016Plug-and-Play ADMM for Image Restoration: Fixed Point Convergence and Applicationscited by 246
- 2021SNIPS: Solving Noisy Inverse Problems Stochasticallycited by 191
- 2022Maximum Likelihood Training for Score-Based Diffusion ODEs by High-Order Denoising Score Matchingcited by 80
- 2014From Denoising to Compressed Sensingcited by 68
- 2017Learned D-AMP: Principled Neural Network based Compressive Image Recoverycited by 65
- 2021Estimating High Order Gradients of the Data Distribution by Denoisingcited by 64
- 2023User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systemscited by 30
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.
Similar, not cited
Close in wording, no citation either way
- 2023Solving Inverse Problems with Score-Based Generative Priors learned from Noisy Data
- 2024Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction
- 2025Compressed Image Generation with Denoising Diffusion Codebook Models
- 2026Stochastic Generative Plug-and-Play Priors
- 2026Taming Score-Based Denoisers in ADMM: A Convergent Plug-and-Play Framework
- 2025Integrating Reweighted Least Squares with Plug-and-Play Diffusion Priors for Noisy Image Restoration
- 2025Exploiting the Exact Denoising Posterior Score in Training-Free Guidance of Diffusion Models
- 2024Plug-and-Play Priors as a Score-Based Method