Performance Analysis of Plug-and-Play ADMM: A Graph Signal Processing Perspective

Abstract

The Plug-and-Play (PnP) alternating direction method of multiplier (ADMM) algorithm is a powerful image restoration framework that allows advanced image denoising priors to be integrated into physical forward models to generate high-quality image restoration results. However, despite the enormous number of applications and several theoretical studies trying to prove convergence by leveraging tools in convex analysis, very little is known about why the algorithm is doing so well. The goal of this paper is to fill the gap by discussing the performance of PnP ADMM. By restricting the denoisers to the class of graph filters under a linearity assumption, or more specifically the symmetric smoothing filters, we offer three contributions: First, we show conditions under which an equivalent maximum- a-posteriori optimization exists; second, we present a geometric interpretation and show that the performance gain is due to an intrinsic predenoising characteristic of the PnP prior; and third, we introduce a new analysis technique via the concept of consensus equilibrium, and provide interpretations to problems involving multiple priors.