[2604.03603] Stochastic Generative Plug-and-Play Priors

Computer Science > Computer Vision and Pattern Recognition arXiv:2604.03603 (cs) [Submitted on 4 Apr 2026] Title:Stochastic Generative Plug-and-Play Priors Authors:Chicago Y. Park, Edward P. Chandler, Yuyang Hu, Michael T. McCann, Cristina Garcia-Cardona, Brendt Wohlberg, Ulugbek S. Kamilov View a PDF of the paper titled Stochastic Generative Plug-and-Play Priors, by Chicago Y. Park and 6 other authors View PDF HTML (experimental) 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 mu...