Plug-and-Play Priors as a Score-Based Method

TL;DR

This paper presents a novel perspective that unifies plug-and-play methods with score-based diffusion models, allowing the use of pre-trained SBMs as priors in PnP algorithms without retraining, facilitating direct comparison and improved image reconstruction.

Contribution

It introduces a new view of PnP as a score-based method, enabling the integration of SBMs into PnP algorithms without retraining and providing mathematical relationships for adaptation.

Findings

Enables reuse of SBMs within PnP algorithms.

Allows direct comparison of PnP and SBM-based methods.

Code implementation available online.

Abstract

Plug-and-play (PnP) methods are extensively used for solving imaging inverse problems by integrating physical measurement models with pre-trained deep denoisers as priors. Score-based diffusion models (SBMs) have recently emerged as a powerful framework for image generation by training deep denoisers to represent the score of the image prior. While both PnP and SBMs use deep denoisers, the score-based nature of PnP is unexplored in the literature due to its distinct origins rooted in proximal optimization. This letter introduces a novel view of PnP as a score-based method, a perspective that enables the re-use of powerful SBMs within classical PnP algorithms without retraining. We present a set of mathematical relationships for adapting popular SBMs as priors within PnP. We show that this approach enables a direct comparison between PnP and SBM-based reconstruction methods using the same neural network as the prior. Code is available at https://github.com/wustl-cig/score_pnp.