HURAULT, Samuel; CHAMBOLLE, Antonin; LECLAIRE, Arthur; PAPADAKIS, Nicolas

doi:10.1007/978-3-031-31975-4_29

Métadonnées

Licence d’utilisation du document

HURAULT, Samuel
Institut de Mathématiques de Bordeaux [IMB]

CHAMBOLLE, Antonin
CEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
Méthodes numériques pour le problème de Monge-Kantorovich et Applications en sciences sociales [MOKAPLAN]

LECLAIRE, Arthur
Institut de Mathématiques de Bordeaux [IMB]

Langue

Communication dans un congrès

Ce document a été publié dans

International Conference on Scale Space and Variational Methods in Computer Vision (SSVM'23), 2023-05-21, Santa Margherita di Pula. 2023-05-21, vol. 14009

Springer

Résumé en anglais

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.< Réduire

Mots clés en anglais

Plug-and-Play

Nonconvex optimization

Inverse problems

URI

https://oskar-bordeaux.fr/handle/20.500.12278/190670

DOI

http://dx.doi.org/10.1007/978-3-031-31975-4_29

Project ANR

Repenser la post-production d'archives avec des méthodes à patch, variationnelles et par apprentissage - ANR-19-CE23-0027
Models, Inference and Synthesis for Texture In Color - ANR-19-CE40-0005

Origine

Importé de hal

Unités de recherche

Institut de Mathématiques de Bordeaux (IMB) - UMR 5251