ENS Lyon "Machine Learning & Signal Processing” seminar

Abstract

Plug-and-Play (PnP) methods constitute a class of iterative algorithms for imaging problems where regularization is performed by an off-the-shelf denoiser. Specifically, given an image dataset, optimizing a function (e.g. a neural network) to remove Gaussian noise is equivalent to approximating the gradient or the proximal operator of the log prior of the training dataset. Therefore, any off-the-shelf denoiser can be used as an implicit prior and inserted into an optimization scheme to restore images. The PnP and Regularization by Denoising (RED) frameworks provide a basis for this approach, for which various convergence analyses have been proposed in the literature. We will more specifically introduce the Gradient Step and Proximal denoisers recently proposed to restore PnP and RED algorithms to their original form as (nonconvex) real proximal splitting algorithms.

Samuel Hurault

Mathematics, Machine Learning, Computer Vision