Afficher la notice abrégée

hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
dc.contributor.authorRENAUD, Marien
hal.structure.identifierMathématiques Appliquées Paris 5 [MAP5 - UMR 8145]
dc.contributor.authorPROST, Jean
hal.structure.identifierImage, Modélisation, Analyse, GEométrie, Synthèse [IMAGES]
hal.structure.identifierDépartement Images, Données, Signal [IDS]
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.accessioned2024-04-04T02:30:10Z
dc.date.available2024-04-04T02:30:10Z
dc.date.issued2024-02-01
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/190243
dc.description.abstractEnPlug-and-Play (PnP) algorithms are a class of iterative algorithms that address image inverse problems by combining a physical model and a deep neural network for regularization. Even if they produce impressive image restoration results, these algorithms rely on a non-standard use of a denoiser on images that are less and less noisy along the iterations, which contrasts with recent algorithms based on Diffusion Models (DM), where the denoiser is applied only on re-noised images. We propose a new PnP framework, called Stochastic deNOising REgularization (SNORE), which applies the denoiser only on images with noise of the adequate level. It is based on an explicit stochastic regularization, which leads to a stochastic gradient descent algorithm to solve ill-posed inverse problems. A convergence analysis of this algorithm and its annealing extension is provided. Experimentally, we prove that SNORE is competitive with respect to state-of-the-art methods on deblurring and inpainting tasks, both quantitatively and qualitatively.
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.enPlug-and-Play image restoration with Stochastic deNOising REgularization
dc.typeDocument de travail - Pré-publication
dc.subject.halStatistiques [stat]/Machine Learning [stat.ML]
dc.identifier.arxiv2402.01779
bordeaux.hal.laboratoriesInstitut de Mathématiques de Bordeaux (IMB) - UMR 5251*
bordeaux.institutionUniversité de Bordeaux
bordeaux.institutionBordeaux INP
bordeaux.institutionCNRS
hal.identifierhal-04440453
hal.version1
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-04440453v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.date=2024-02-01&rft.au=RENAUD,%20Marien&PROST,%20Jean&LECLAIRE,%20Arthur&PAPADAKIS,%20Nicolas&rft.genre=preprint


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