Mostrar el registro sencillo del ítem

Accelerating GMM-based patch priors for image restoration: Three ingredients for a 100x speed-up

hal.structure.identifierUniversity of California [San Diego] [UC San Diego]
dc.contributor.authorPARAMESWARAN, Shibin
hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
hal.structure.identifierUniversity of California [San Diego] [UC San Diego]
dc.contributor.authorDELEDALLE, Charles-Alban
hal.structure.identifierUniversité Jean Monnet - Saint-Étienne [UJM]
hal.structure.identifierUniversité de Lyon
hal.structure.identifierInstitut d'Optique Graduate School [IOGS]
hal.structure.identifierLaboratoire Hubert Curien [LabHC]
dc.contributor.authorDENIS, Loïc
hal.structure.identifierUniversity of California [San Diego] [UC San Diego]
dc.contributor.authorNGUYEN, Truong Q.
hal.structure.identifierCentre de Géosciences [GEOSCIENCES]
dc.contributor.authorNGUYEN, Truong
dc.date.accessioned2024-04-04T03:05:22Z
dc.date.available2024-04-04T03:05:22Z
dc.date.created2017-10-16
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/193239
dc.description.abstractEnImage restoration methods aim to recover the underlying clean image from corrupted observations. The Expected Patch Log-likelihood (EPLL) algorithm is a powerful image restoration method that uses a Gaussian mixture model (GMM) prior on the patches of natural images. Although it is very effective for restoring images, its high runtime complexity makes EPLL ill-suited for most practical applications. In this paper, we propose three approximations to the original EPLL algorithm. The resulting algorithm, which we call the fast-EPLL (FEPLL), attains a dramatic speed-up of two orders of magnitude over EPLL while incurring a negligible drop in the restored image quality (less than 0.5 dB). We demonstrate the efficacy and versatility of our algorithm on a number of inverse problems such as denoising, deblurring, super-resolution, inpainting and devignetting. To the best of our knowledge, FEPLL is the first algorithm that can competitively restore a 512x512 pixel image in under 0.5s for all the degradations mentioned above without specialized code optimizations such as CPU parallelization or GPU implementation.
dc.language.isoen
dc.subject.enIndex Terms—Image restoration
dc.subject.enImage restoration
dc.subject.enefficient algorithms
dc.subject.enGaussian mix- ture model
dc.subject.enimage patch
dc.subject.enGaussian mixture model
dc.title.enAccelerating GMM-based patch priors for image restoration: Three ingredients for a 100x speed-up
dc.typeDocument de travail - Pré-publication
dc.subject.halInformatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]
dc.subject.halSciences de l'ingénieur [physics]/Traitement du signal et de l'image
dc.subject.halInformatique [cs]/Traitement des images
dc.subject.halInformatique [cs]/Traitement du signal et de l'image
dc.identifier.arxiv1710.08124
bordeaux.hal.laboratoriesInstitut de Mathématiques de Bordeaux (IMB) - UMR 5251*
bordeaux.institutionUniversité de Bordeaux
bordeaux.institutionBordeaux INP
bordeaux.institutionCNRS
hal.identifierhal-01617722
hal.version1
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-01617722v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.au=PARAMESWARAN,%20Shibin&DELEDALLE,%20Charles-Alban&DENIS,%20Lo%C3%AFc&NGUYEN,%20Truong%20Q.&NGUYEN,%20Truong&rft.genre=preprint


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