Plug-and-Play Priors as a Score-Based Method
This provides a novel perspective for researchers in computational imaging, allowing direct comparison between PnP and SBM-based reconstruction methods using the same neural network prior.
The paper tackles the problem of solving imaging inverse problems by showing that plug-and-play (PnP) methods can be viewed as score-based methods, enabling the reuse of powerful score-based diffusion models (SBMs) within PnP algorithms without retraining.
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.