A relaxed proximal gradient descent algorithm for convergent plug-and-play with proximal denoiser - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

A relaxed proximal gradient descent algorithm for convergent plug-and-play with proximal denoiser

Résumé

This paper presents a new convergent Plug-and-Play (PnP) algorithm. PnP methods are efficient iterative algorithms for solving image inverse problems formulated as the minimization of the sum of a data-fidelity term and a regularization term. PnP methods perform regularization by plugging a pre-trained denoiser in a proximal algorithm, such as Proximal Gradient Descent (PGD). To ensure convergence of PnP schemes, many works study specific parametrizations of deep denoisers. However, existing results require either unverifiable or suboptimal hypotheses on the denoiser, or assume restrictive conditions on the parameters of the inverse problem. Observing that these limitations can be due to the proximal algorithm in use, we study a relaxed version of the PGD algorithm for minimizing the sum of a convex function and a weakly convex one. When plugged with a relaxed proximal denoiser, we show that the proposed PnP-$\alpha$PGD algorithm converges for a wider range of regularization parameters, thus allowing more accurate image restoration.

Dates et versions

hal-03967018 , version 1 (01-02-2023)

Identifiants

Citer

Samuel Hurault, Antonin Chambolle, Arthur Leclaire, Nicolas Papadakis. A relaxed proximal gradient descent algorithm for convergent plug-and-play with proximal denoiser. International Conference on Scale Space and Variational Methods in Computer Vision (SSVM'23), May 2023, Santa Margherita di Pula, Italy. ⟨10.1007/978-3-031-31975-4_29⟩. ⟨hal-03967018⟩
38 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More