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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Park, Chicago Y., Hu, Yuyang, McCann, Michael T., Garcia-Cardona, Cristina, Wohlberg, Brendt, Kamilov, Ulugbek S.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909821851140096
author Park, Chicago Y.
Hu, Yuyang
McCann, Michael T.
Garcia-Cardona, Cristina
Wohlberg, Brendt
Kamilov, Ulugbek S.
author_facet Park, Chicago Y.
Hu, Yuyang
McCann, Michael T.
Garcia-Cardona, Cristina
Wohlberg, Brendt
Kamilov, Ulugbek S.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_11108
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Plug-and-Play Priors as a Score-Based Method
Park, Chicago Y.
Hu, Yuyang
McCann, Michael T.
Garcia-Cardona, Cristina
Wohlberg, Brendt
Kamilov, Ulugbek S.
Image and Video Processing
Computer Vision and Pattern Recognition
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.
title Plug-and-Play Priors as a Score-Based Method
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.11108