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 .

翻译：过去十年间，即插即用（PnP）方法已成为一种流行的图像重建技术，其采用由前向模型与先验模型组成的模块化框架。PnP的核心优势在于，图像去噪器可作为先验模型使用，而前向模型则可通过更传统的物理驱动方法实现。然而，PnP的局限性在于其仅能重建单一确定性图像。本文提出生成式即插即用（GPnP），将PnP推广至后验分布采样。与PnP类似，GPnP采用基于物理的前向模型与图像去噪先验模型构成的模块化框架。但在GPnP中，这些模型被扩展为近端生成器，用于从关联分布中采样。GPnP通过交替应用这些近端生成器，生成来自后验分布的样本。我们利用经典BM3D去噪器开展实验仿真，结果表明GPnP方法具有鲁棒性、易于实现的特点，并能针对稀疏插值与层析重建任务生成直觉上合理的后验分布样本。本文配套代码见https://github.com/gbuzzard/generative-pnp-allerton。