Afficher la notice abrégée

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

hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
dc.contributor.authorHURAULT, Samuel
hal.structure.identifierCEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
hal.structure.identifierMéthodes numériques pour le problème de Monge-Kantorovich et Applications en sciences sociales [MOKAPLAN]
dc.contributor.authorCHAMBOLLE, Antonin
hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
dc.contributor.authorLECLAIRE, Arthur
hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
dc.contributor.authorPAPADAKIS, Nicolas
dc.contributor.editorLuca Calatroni
dc.contributor.editorMarco Donatelli
dc.contributor.editorSerena Morigi
dc.contributor.editorMarco Prato
dc.contributor.editorMatteo Santacesaria
dc.date.accessioned2024-04-04T02:35:46Z
dc.date.available2024-04-04T02:35:46Z
dc.date.issued2023-05-21
dc.date.conference2023-05-21
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/190670
dc.description.abstractEnThis 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.
dc.description.sponsorshipRepenser la post-production d'archives avec des méthodes à patch, variationnelles et par apprentissage - ANR-19-CE23-0027
dc.description.sponsorshipModels, Inference and Synthesis for Texture In Color - ANR-19-CE40-0005
dc.language.isoen
dc.publisherSpringer
dc.subject.enPlug-and-Play
dc.subject.enNonconvex optimization
dc.subject.enInverse problems
dc.title.enA relaxed proximal gradient descent algorithm for convergent plug-and-play with proximal denoiser
dc.typeCommunication dans un congrès
dc.identifier.doi10.1007/978-3-031-31975-4_29
dc.subject.halStatistiques [stat]/Machine Learning [stat.ML]
dc.subject.halInformatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]
dc.subject.halInformatique [cs]/Traitement des images
dc.subject.halMathématiques [math]/Optimisation et contrôle [math.OC]
dc.identifier.arxiv2301.13731v2
bordeaux.volume14009
bordeaux.hal.laboratoriesInstitut de Mathématiques de Bordeaux (IMB) - UMR 5251*
bordeaux.institutionUniversité de Bordeaux
bordeaux.institutionBordeaux INP
bordeaux.institutionCNRS
bordeaux.conference.titleInternational Conference on Scale Space and Variational Methods in Computer Vision (SSVM'23)
bordeaux.countryIT
bordeaux.conference.citySanta Margherita di Pula
bordeaux.peerReviewedoui
hal.identifierhal-03967018
hal.version1
hal.invitednon
hal.proceedingsoui
hal.conference.end2023-05-25
hal.popularnon
hal.audienceInternationale
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-03967018v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.date=2023-05-21&rft.volume=14009&rft.au=HURAULT,%20Samuel&CHAMBOLLE,%20Antonin&LECLAIRE,%20Arthur&PAPADAKIS,%20Nicolas&rft.genre=unknown


Fichier(s) constituant ce document

FichiersTailleFormatVue

Il n'y a pas de fichiers associés à ce document.

Ce document figure dans la(les) collection(s) suivante(s)

Afficher la notice abrégée