MACHINE LEARNING BASED DYNAMIC COMPOSING IN ENHANCED STANDARD DYNAMIC RANGE VIDEO (SDR+)

Training image pairs comprising training SDR image and corresponding training HDR images are received. Each training image pair in the training image pairs comprises a training SDR image and a corresponding training HDR image. The training SDR image and the corresponding training HDR image in the tr...

Full description

Saved in:
Bibliographic Details
Main Authors SU, Guan-Ming, GADGIL, Neeraj J, KADU, Harshad
Format Patent
LanguageEnglish
French
Published 25.06.2020
Subjects
Online AccessGet full text

Cover

Loading…
Abstract Training image pairs comprising training SDR image and corresponding training HDR images are received. Each training image pair in the training image pairs comprises a training SDR image and a corresponding training HDR image. The training SDR image and the corresponding training HDR image in the training image pair depict same visual content but with different luminance dynamic ranges. Training image feature vectors are extracted from training SDR images in the training image pairs. The training image feature vectors are used to train backward reshaping metadata prediction models for predicting operational parameter values of backward reshaping mappings used to backward reshape SDR images into mapped HDR images. Selon la présente invention, des paires d'images de formation comprenant une image SDR de formation et des images HDR de formation correspondantes sont reçues. Chaque paire d'images de formation des paires d'images de formation comprend une image SDR de formation et une image HDR de formation correspondante. L'image SDR de formation et l'image HDR de formation correspondante de la paire d'images de formation présentent le même contenu visuel mais avec des plages dynamiques de luminance différentes. Des vecteurs caractéristiques d'images de formation sont extraits d'images SDR de formation des paires d'images de formation. Les vecteurs caractéristiques d'images de formation sont utilisés pour former des modèles de prédiction de métadonnées de rétro-remodelage pour prédire des valeurs de paramètres opérationnels de mappages de rétro-remodelage utilisés pour rétro-remodeler des images SDR en images HDR mappées.
AbstractList Training image pairs comprising training SDR image and corresponding training HDR images are received. Each training image pair in the training image pairs comprises a training SDR image and a corresponding training HDR image. The training SDR image and the corresponding training HDR image in the training image pair depict same visual content but with different luminance dynamic ranges. Training image feature vectors are extracted from training SDR images in the training image pairs. The training image feature vectors are used to train backward reshaping metadata prediction models for predicting operational parameter values of backward reshaping mappings used to backward reshape SDR images into mapped HDR images. Selon la présente invention, des paires d'images de formation comprenant une image SDR de formation et des images HDR de formation correspondantes sont reçues. Chaque paire d'images de formation des paires d'images de formation comprend une image SDR de formation et une image HDR de formation correspondante. L'image SDR de formation et l'image HDR de formation correspondante de la paire d'images de formation présentent le même contenu visuel mais avec des plages dynamiques de luminance différentes. Des vecteurs caractéristiques d'images de formation sont extraits d'images SDR de formation des paires d'images de formation. Les vecteurs caractéristiques d'images de formation sont utilisés pour former des modèles de prédiction de métadonnées de rétro-remodelage pour prédire des valeurs de paramètres opérationnels de mappages de rétro-remodelage utilisés pour rétro-remodeler des images SDR en images HDR mappées.
Author SU, Guan-Ming
KADU, Harshad
GADGIL, Neeraj J
Author_xml – fullname: SU, Guan-Ming
– fullname: GADGIL, Neeraj J
– fullname: KADU, Harshad
BookMark eNrjYmDJy89L5WSI8HV09vD0c1XwcXUM8vP0c1dwcgx2dVFwifRz9PV0VnD29w3wDwaJe_opuPp5OPo5A2WDQxz9XByDEMqCHP3cXRXCPF1c_RU0gl2CtDV5GFjTEnOKU3mhNDeDsptriLOHbmpBfnxqcUFicmpeakl8uL-RgZGBobGhubGho6ExcaoAk18y-Q
ContentType Patent
DBID EVB
DatabaseName esp@cenet
DatabaseTitleList
Database_xml – sequence: 1
  dbid: EVB
  name: esp@cenet
  url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Chemistry
Sciences
DocumentTitleAlternate COMPOSITION DYNAMIQUE BASÉE SUR L'APPRENTISSAGE MACHINE DANS UNE VIDÉO À PLAGE DYNAMIQUE STANDARD AMÉLIORÉE (SDR +)
ExternalDocumentID WO2020131731A1
GroupedDBID EVB
ID FETCH-epo_espacenet_WO2020131731A13
IEDL.DBID EVB
IngestDate Fri Sep 20 10:16:31 EDT 2024
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
French
LinkModel DirectLink
MergedId FETCHMERGED-epo_espacenet_WO2020131731A13
Notes Application Number: WO2019US66595
OpenAccessLink https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20200625&DB=EPODOC&CC=WO&NR=2020131731A1
ParticipantIDs epo_espacenet_WO2020131731A1
PublicationCentury 2000
PublicationDate 20200625
PublicationDateYYYYMMDD 2020-06-25
PublicationDate_xml – month: 06
  year: 2020
  text: 20200625
  day: 25
PublicationDecade 2020
PublicationYear 2020
RelatedCompanies DOLBY LABORATORIES LICENSING CORPORATION
RelatedCompanies_xml – name: DOLBY LABORATORIES LICENSING CORPORATION
Score 3.2758453
Snippet Training image pairs comprising training SDR image and corresponding training HDR images are received. Each training image pair in the training image pairs...
SourceID epo
SourceType Open Access Repository
SubjectTerms ELECTRIC COMMUNICATION TECHNIQUE
ELECTRICITY
PICTORIAL COMMUNICATION, e.g. TELEVISION
Title MACHINE LEARNING BASED DYNAMIC COMPOSING IN ENHANCED STANDARD DYNAMIC RANGE VIDEO (SDR+)
URI https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20200625&DB=EPODOC&locale=&CC=WO&NR=2020131731A1
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dS8MwEA9jivqmU_FjSkApihS3Ntm6hyFZkq0Vm452zvk01rUDQbrhKv77Xsqme9pbvjiSg1_ufsldgtBtM3EondLYtGaObZKkBpCySMNspOCNWGRCarZOTvZVw30lzyM6KqHPdS5M8U7oT_E4IiBqCnjPi_168X-IJYrYyuVj_AFN86fuoC2MFTvW_Niihui0ZT8QATc4B95mqLDoq4OttOsMuNIOONJNjQc57Oi8lMWmUekeot0-yMvyI1RKswra5-u_1ypoz19deUNxhb7lMRr5jLuekvhFslB5qoc7LJICi3fFQJuYB34_iHS7p7BUrv53RuBowJRg4f-wkKmexENPyADfRSJ8uD9BN1054K4JUxz_aWT8Fmyuxz5F5WyepWcI15N0Npk5YJicFokn0zhpJcAQaUJbDiGxfY6q2yRdbO--RAe6qiOlLFpF5fzrO70Cm5zH14UqfwE_AIZU
link.rule.ids 230,309,783,888,25576,76876
linkProvider European Patent Office
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3fT8IwEG6IGvFNUeMP1CaaRWMWYWthPBBT1sKmrCPbRHwijI3ExACRGf99rwsIT7w1d03TXvL17mvvWoTu6olF6ZjGujGxTJ0kFYCUQWp6LYVoxCAjUjFVcbIna84beRnQQQF9rWph8ndCf_PHEQFRY8B7lu_X8_UhFs9zKxdP8SeIZs_tqMm1JTtW_NigGm81Rc_nvq3ZNvA2TQa5rgq-0qwy4Eq7EGTXFR5Ev6XqUuabTqV9iPZ6MN40O0KFdFpCRXv191oJ7XvLK29oLtG3OEYDj9mOKwXuChZIV3Zwi4WCY_4hGVgT277X80MldyUW0lH_znAcRkxyFqy7BUx2BO67XPj4PuTB48MJum2LyHZ0mOLw3yLDd39zPeYp2pnOpukZwtUknYwmFjgmq0Hi0ThOGgkwRJrQhkVIbJ6j8raRLrarb1DRibzusOvK10t0oFQqa8qgZbSTff-kV-Cfs_g6N-sfuG-JRw
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=MACHINE+LEARNING+BASED+DYNAMIC+COMPOSING+IN+ENHANCED+STANDARD+DYNAMIC+RANGE+VIDEO+%28SDR%2B%29&rft.inventor=SU%2C+Guan-Ming&rft.inventor=GADGIL%2C+Neeraj+J&rft.inventor=KADU%2C+Harshad&rft.date=2020-06-25&rft.externalDBID=A1&rft.externalDocID=WO2020131731A1