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...
Saved in:
Main Authors | , , |
---|---|
Format | Patent |
Language | English French |
Published |
25.06.2020
|
Subjects | |
Online Access | Get 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 |