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

2024/12/15 by Chicago Y. Park, Yuyang Hu, Park, Chicago Y. +9 · 2 citations
Psychology · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Psychiatric care and mental health services #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2412.11108

openalex publication_date 2024/12/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Cited by

• Deep Parameter Interpolation for Scalar Conditioning
• Consistency Models as Plug-and-Play Priors for Inverse Problems

Related

• Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction
• Scalable Plug-and-Play ADMM with Convergence Guarantees
• Score-Based Diffusion Models as Principled Priors for Inverse Imaging
• Diff-Unfolding: A Model-Based Score Learning Framework for Inverse Problems
• Analysis Plug-and-Play Methods for Imaging Inverse Problems