Mostrar el registro sencillo del ítem

Convergent Bregman Plug-and-Play Image Restoration for Poisson Inverse Problems

hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
dc.contributor.authorHURAULT, Samuel
hal.structure.identifierWashington University in Saint Louis [WUSTL]
dc.contributor.authorKAMILOV, Ulugbek
hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
hal.structure.identifierTélécom Paris
dc.contributor.authorLECLAIRE, Arthur
hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
hal.structure.identifierModélisation Mathématique pour l'Oncologie [MONC]
dc.contributor.authorPAPADAKIS, Nicolas
dc.date.accessioned2024-04-04T02:34:04Z
dc.date.available2024-04-04T02:34:04Z
dc.date.issued2023-12-10
dc.date.conference2023-12-10
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/190528
dc.description.abstractEnPlug-and-Play (PnP) methods are efficient iterative algorithms for solving ill-posed image inverse problems. PnP methods are obtained by using deep Gaussian denoisers instead of the proximal operator or the gradient-descent step within proximal algorithms. Current PnP schemes rely on data-fidelity terms that have either Lipschitz gradients or closed-form proximal operators, which is not applicable to Poisson inverse problems. Based on the observation that the Gaussian noise is not the adequate noise model in this setting, we propose to generalize PnP using theBregman Proximal Gradient (BPG) method. BPG replaces the Euclidean distance with a Bregman divergence that can better capture the smoothness properties of the problem. We introduce the Bregman Score Denoiser specifically parametrized and trained for the new Bregman geometry and prove that it corresponds to the proximal operator of a nonconvex potential. We propose two PnP algorithms based on the Bregman Score Denoiser for solving Poisson inverse problems. Extending the convergence results of BPG in the nonconvex settings, we show that the proposed methods converge, targeting stationary points of an explicit global functional. Experimental evaluations conducted on various Poisson inverse problems validate the convergence results and showcase effective restoration performance.
dc.description.sponsorshipModels, Inference and Synthesis for Texture In Color - ANR-19-CE40-0005
dc.description.sponsorshipRepenser la post-production d'archives avec des méthodes à patch, variationnelles et par apprentissage - ANR-19-CE23-0027
dc.language.isoen
dc.title.enConvergent Bregman Plug-and-Play Image Restoration for Poisson Inverse Problems
dc.typeCommunication dans un congrès
dc.subject.halInformatique [cs]/Apprentissage [cs.LG]
dc.subject.halInformatique [cs]/Intelligence artificielle [cs.AI]
dc.identifier.arxiv2306.03466
bordeaux.hal.laboratoriesInstitut de Mathématiques de Bordeaux (IMB) - UMR 5251*
bordeaux.institutionUniversité de Bordeaux
bordeaux.institutionBordeaux INP
bordeaux.institutionCNRS
bordeaux.conference.titleNeural Information Processing Systems (NeurIPS'23)
bordeaux.countryUS
bordeaux.conference.cityNew Orleans
bordeaux.peerReviewedoui
hal.identifierhal-04121529
hal.version1
hal.invitednon
hal.proceedingsoui
hal.conference.end2023-12-16
hal.popularnon
hal.audienceInternationale
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-04121529v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.date=2023-12-10&rft.au=HURAULT,%20Samuel&KAMILOV,%20Ulugbek&LECLAIRE,%20Arthur&PAPADAKIS,%20Nicolas&rft.genre=unknown


Archivos en el ítem

ArchivosTamañoFormatoVer

No hay archivos asociados a este ítem.

Este ítem aparece en la(s) siguiente(s) colección(ones)

Mostrar el registro sencillo del ítem