Stochastic Generative Plug-and-Play Priors

• URL: http://arxiv.org/abs/2604.03603v1
• Date: Sat, 04 Apr 2026 06:14:38 GMT
• Title: Stochastic Generative Plug-and-Play Priors
• Abstract summary: Plug-and-play (M) methods are widely used for solving inverse imaging problems by incorporating a denoiser into optimization algorithms.<n>Score-based diffusion models (SBDMs) have recently demonstrated strong generative performance through a denoiser trained across a range of levels.<n>It remains unclear how to systematically use SBDMs as priors within a framework without relying on reverse diffusion sampling.
• Score: 9.429516239444922
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Plug-and-play (PnP) methods are widely used for solving imaging inverse problems by incorporating a denoiser into optimization algorithms. Score-based diffusion models (SBDMs) have recently demonstrated strong generative performance through a denoiser trained across a wide range of noise levels. Despite their shared reliance on denoisers, it remains unclear how to systematically use SBDMs as priors within the PnP framework without relying on reverse diffusion sampling. In this paper, we establish a score-based interpretation of PnP that justifies using pretrained SBDMs directly within PnP algorithms. Building on this connection, we introduce a stochastic generative PnP (SGPnP) framework that injects noise to better leverage the expressive generative SBDM priors, thereby improving robustness in severely ill-posed inverse problems. We provide a new theory showing that this noise injection induces optimization on a Gaussian-smoothed objective and promotes escape from strict saddle points. Experiments on challenging inverse tasks, such as multi-coil MRI reconstruction and large-mask natural image inpainting, demonstrate consistent improvement over conventional PnP methods and achieve performance competitive with diffusion-based solvers.

Related papers

• FlowADMM: Plug-and-play ADMM with Flow-based Renoise-Denoise Priors [2.986668330518244]
  FlowADMM is a state-of-the-art flow-based generative algorithm for solving inverse problems.<n>We show that FlowADMM achieves a state-of-the-art performance among flow-based generative methods on a range of inverse problems.
  arXiv  Detail & Related papers  (2026-05-09T03:21:01Z)
• V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think [90.69263509098948]
  We introduce Variational GRPO, a method that integrates ELBO-based surrogates with the Group Relative Policy Optimization algorithm.<n>V-GRPO achieves state-of-the-art performance in text-to-image synthesis, while delivering a $2times$ speedup over MixGRPO and a $3times$ speedup over DiffusionNFT.
  arXiv  Detail & Related papers  (2026-04-25T17:03:21Z)
• Integrating Reweighted Least Squares with Plug-and-Play Diffusion Priors for Noisy Image Restoration [6.402777145722335]
  We propose a plug-and-play image restoration framework based on generative diffusion priors for robust removal of general noise types, including impulse noise.<n> Experimental results on benchmark datasets demonstrate that the proposed method effectively removes non-Gaussian impulse noise and achieves superior restoration performance.
  arXiv  Detail & Related papers  (2025-11-10T08:11:20Z)
• G$^2$RPO: Granular GRPO for Precise Reward in Flow Models [74.21206048155669]
  We propose a novel Granular-GRPO (G$2$RPO) framework that achieves precise and comprehensive reward assessments of sampling directions.<n>We introduce a Multi-Granularity Advantage Integration module that aggregates advantages computed at multiple diffusion scales.<n>Our G$2$RPO significantly outperforms existing flow-based GRPO baselines.
  arXiv  Detail & Related papers  (2025-10-02T12:57:12Z)
• Inference-Time Scaling of Diffusion Language Models with Particle Gibbs Sampling [70.8832906871441]
  We study how to steer generation toward desired rewards without retraining the models.<n>Prior methods typically resample or filter within a single denoising trajectory, optimizing rewards step-by-step without trajectory-level refinement.<n>We introduce particle Gibbs sampling for diffusion language models (PG-DLM), a novel inference-time algorithm enabling trajectory-level refinement while preserving generation perplexity.
  arXiv  Detail & Related papers  (2025-07-11T08:00:47Z)
• Plug-and-Play Priors as a Score-Based Method [10.533522753705599]
  Plug-and-play (pn) methods are extensively used for solving inverse problems by integrating physical measurement models with pre-trained deep denoisers as priors.<n>Score-based diffusion models (SBMs) have recently emerged as a powerful framework for image generation by deep deep denoisers to represent the score of the image prior.
  arXiv  Detail & Related papers  (2024-12-15T08:10:39Z)
• Arbitrary-steps Image Super-resolution via Diffusion Inversion [68.78628844966019]
  This study presents a new image super-resolution (SR) technique based on diffusion inversion, aiming at harnessing the rich image priors encapsulated in large pre-trained diffusion models to improve SR performance.<n>We design a Partial noise Prediction strategy to construct an intermediate state of the diffusion model, which serves as the starting sampling point.<n>Once trained, this noise predictor can be used to initialize the sampling process partially along the diffusion trajectory, generating the desirable high-resolution result.
  arXiv  Detail & Related papers  (2024-12-12T07:24:13Z)
• PnP-Flow: Plug-and-Play Image Restoration with Flow Matching [9.589644878034553]
  We introduce Plug-and-Play Flow Matching, an algorithm for solving inverse imaging problems.<n>We evaluate its performance on denoising, superresolution, and inpainting tasks.
  arXiv  Detail & Related papers  (2024-10-03T12:13:56Z)
• Prior Mismatch and Adaptation in PnP-ADMM with a Nonconvex Convergence Analysis [20.63188897629508]
  Plug-and-Play priors is a widely-used family methods for solving inverse imaging problems. Deep methods have been shown to achieve state-of-the-art performance when the prior is obtained using powerful denoisers.
  arXiv  Detail & Related papers  (2023-09-29T20:49:00Z)
• Score-Guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problem [97.64313409741614]
  We prove fast mixing and characterize the stationary distribution of the Langevin Algorithm for inverting random weighted DNN generators. We propose to do posterior sampling in the latent space of a pre-trained generative model.
  arXiv  Detail & Related papers  (2022-06-18T03:47:37Z)
• Recovery Analysis for Plug-and-Play Priors using the Restricted Eigenvalue Condition [48.08511796234349]
  We show how to establish theoretical recovery guarantees for the plug-and-play priors (noise) and regularization by denoising (RED) methods. Our results suggest that models with a pre-trained artifact removal network provides significantly better results compared to existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-06-07T14:45:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.