PnP-ReG: Learned Regularizing Gradient for Plug-and-Play Gradient Descent. (arXiv:2204.13940v2 [eess.IV] UPDATED)

The Plug-and-Play (PnP) framework makes it possible to integrate advanced
image denoising priors into optimization algorithms, to efficiently solve a
variety of image restoration tasks generally formulated as Maximum A Posteriori
(MAP) estimation problems. The Plug-and-Play alternating direction method of
multipliers (ADMM) and the Regularization by Denoising (RED) algorithms are two
examples of such methods that made a breakthrough in image restoration.
However, while the former method only applies to proximal algorithms, it has
recently been shown that there exists …

arxiv gradient pnp