Proximal denoiser for convergent plug-and-play optimization with nonconvex regularization - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Proximal denoiser for convergent plug-and-play optimization with nonconvex regularization

Samuel Hurault
  • Fonction : Auteur
Arthur Leclaire

Résumé

Plug-and-Play (PnP) methods solve ill-posed inverse problems through iterative proximal algorithms by replacing a proximal operator by a denoising operation. When applied with deep neural network denoisers, these methods have shown state-of-the-art visual performance for image restoration problems. However, their theoretical convergence analysis is still incomplete. Most of the existing convergence results consider nonexpansive denoisers, which is non-realistic, or limit their analysis to strongly convex data-fidelity terms in the inverse problem to solve. Recently, it was proposed to train the denoiser as a gradient descent step on a functional parameterized by a deep neural network. Using such a denoiser guarantees the convergence of the PnP version of the Half-Quadratic-Splitting (PnP-HQS) iterative algorithm. In this paper, we show that this gradient denoiser can actually correspond to the proximal operator of another scalar function. Given this new result, we exploit the convergence theory of proximal algorithms in the nonconvex setting to obtain convergence results for PnP-PGD (Proximal Gradient Descent) and PnP-ADMM (Alternating Direction Method of Multipliers). When built on top of a smooth gradient denoiser, we show that PnP-PGD and PnP-ADMM are convergent and target stationary points of an explicit functional. These convergence results are confirmed with numerical experiments on deblurring, super-resolution and inpainting.

Dates et versions

hal-03550371 , version 1 (01-02-2022)

Identifiants

Citer

Samuel Hurault, Arthur Leclaire, Nicolas Papadakis. Proximal denoiser for convergent plug-and-play optimization with nonconvex regularization. International Conference on Machine Learning (ICML'22), Jul 2022, Baltimore, United States. ⟨hal-03550371⟩

Collections

CNRS ANR
48 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More