Afficher la notice abrégée

Learning Defects in Old Movies from Manually Assisted Restoration

hal.structure.identifierReal Expression Artificial Life [IRIT-REVA]
dc.contributor.authorRENAUDEAU, Arthur
hal.structure.identifierReal Expression Artificial Life [IRIT-REVA]
dc.contributor.authorSENG, Travis
hal.structure.identifierReal Expression Artificial Life [IRIT-REVA]
hal.structure.identifierInstitut National Polytechnique (Toulouse) [Toulouse INP]
dc.contributor.authorCARLIER, Axel
hal.structure.identifierLaboratoire Lorrain de Recherche en Informatique et ses Applications [LORIA]
hal.structure.identifierAugmentation visuelle d'environnements complexes [MAGRIT-POST]
hal.structure.identifierVisual Augmentation of Complex Environments [MAGRIT]
dc.contributor.authorPIERRE, Fabien
hal.structure.identifierDepartment of Computer Science [Copenhagen] [DIKU]
dc.contributor.authorLAUZE, François
hal.structure.identifierInstitut de Mathématiques de Bordeaux [IMB]
dc.contributor.authorAUJOL, Jean-François
hal.structure.identifierReal Expression Artificial Life [IRIT-REVA]
dc.contributor.authorDUROU, Jean-Denis
dc.date.accessioned2024-04-04T02:49:15Z
dc.date.available2024-04-04T02:49:15Z
dc.date.conference2020-09-13
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/191806
dc.description.abstractEnWe propose to detect defects in old movies, as the first step of a larger framework of old movies restoration by inpainting techniques. The specificity of our work is to learn a film restorer's expertise from a pair of sequences, composed of a movie with defects, and the same movie which was semi-automatically restored with the help of a specialized software. In order to detect those defects with minimal human interaction and further reduce the time spent for a restoration, we feed a U-Net with consecutive defective frames as input to detect the unexpected variations of pixel intensity over space and time. Since the output of the network is a mask of defect location, we first have to create the dataset of mask frames on the basis of restored frames from the software used by the film restorer, instead of classical synthetic ground truth, which is not available. These masks are estimated by computing the absolute difference between restored frames and defectuous frames, combined with thresholding and morphological closing. Our network succeeds in automatically detecting real defects with more precision than the manual selection with an all-encompassing shape, including some the expert restorer could have missed for lack of time.
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.enLearning Defects in Old Movies from Manually Assisted Restoration
dc.typeCommunication dans un congrès
dc.subject.halInformatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]
bordeaux.hal.laboratoriesInstitut de Mathématiques de Bordeaux (IMB) - UMR 5251*
bordeaux.institutionUniversité de Bordeaux
bordeaux.institutionBordeaux INP
bordeaux.institutionCNRS
bordeaux.conference.titleICPR 2020 - 25th International Conference on Pattern Recognition
bordeaux.countryIT
bordeaux.conference.cityMilan / Virtual
bordeaux.peerReviewedoui
hal.identifierhal-02965296
hal.version1
hal.invitednon
hal.proceedingsoui
hal.conference.end2020-09-18
hal.popularnon
hal.audienceInternationale
hal.origin.linkhttps://hal.archives-ouvertes.fr//hal-02965296v1
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.au=RENAUDEAU,%20Arthur&SENG,%20Travis&CARLIER,%20Axel&PIERRE,%20Fabien&LAUZE,%20Fran%C3%A7ois&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