Mostrar el registro sencillo del ítem

Inverse problem regularization with hierarchical variational autoencoders

hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
dc.contributor.authorPROST, Jean
hal.structure.identifierUbisoft
dc.contributor.authorHOUDARD, Antoine
hal.structure.identifierMathématiques Appliquées Paris 5 [MAP5 - UMR 8145]
dc.contributor.authorALMANSA, Andres
hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
hal.structure.identifierModélisation Mathématique pour l'Oncologie [MONC]
dc.contributor.authorPAPADAKIS, Nicolas
dc.date.accessioned2024-04-04T02:34:52Z
dc.date.available2024-04-04T02:34:52Z
dc.date.issued2023-03-20
dc.date.conference2023-10-02
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/190583
dc.description.abstractEnIn this paper, we propose to regularize ill-posed inverse problems using a deep hierarchical variational autoencoder (HVAE) as an image prior. The proposed method synthesizes the advantages of i) denoiser-based Plug \& Play approaches and ii) generative model based approaches to inverse problems. First, we exploit VAE properties to design an efficient algorithm that benefits from convergence guarantees of Plug-and-Play (PnP) methods. Second, our approach is not restricted to specialized datasets and the proposed PnP-HVAE model is able to solve image restoration problems on natural images of any size. Our experiments show that the proposed PnP-HVAE method is competitive with both SOTA denoiser-based PnP approaches, and other SOTA restoration methods based on generative models.
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.enInverse problem regularization with hierarchical variational autoencoders
dc.typeCommunication dans un congrès
dc.subject.halInformatique [cs]
dc.identifier.arxiv2303.11217
bordeaux.hal.laboratoriesInstitut de Mathématiques de Bordeaux (IMB) - UMR 5251*
bordeaux.institutionUniversité de Bordeaux
bordeaux.institutionBordeaux INP
bordeaux.institutionCNRS
bordeaux.conference.titleIEEE International Conference on Computer Vision (ICCV'23)
bordeaux.countryFR
bordeaux.conference.cityParis
bordeaux.peerReviewedoui
hal.identifierhal-04038644
hal.version1
hal.invitednon
hal.proceedingsoui
hal.conference.end2023-10-06
hal.popularnon
hal.audienceInternationale
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-04038644v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.date=2023-03-20&rft.au=PROST,%20Jean&HOUDARD,%20Antoine&ALMANSA,%20Andres&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