Vision models fine-tuned by cinema professionals for High Dynamic Range imaging in movies

Many challenges that deal with processing of HDR material remain very much open for the film industry, whose extremely demanding quality standards are not met by existing automatic methods. Therefore, when dealing with HDR content, substantial work by very skilled technicians has to be carried out a...

ver descrição completa

Detalhes bibliográficos
Autores: Cyriac, Praveen, Canham, Trevor, Kane, David, Bertalmío, Marcelo
Tipo de documento: artigo
Estado:Versão publicada
Data de publicação:2020
País:España
Recursos:Universitat Pompeu Fabra
Repositório:Repositorio Digital de la UPF
OAI Identifier:oai:repositori.upf.edu:10230/45415
Acesso em linha:http://hdl.handle.net/10230/45415
http://dx.doi.org/10.1007/s11042-020-09532-y
Access Level:Acceso aberto
Palavra-chave:High dynamic range
Vision models
Visual perception
Tone mapping
Inverse tone mapping
Cinema post-production
id ES_99ea39f03e35484259f4ecb03332000e
oai_identifier_str oai:repositori.upf.edu:10230/45415
network_acronym_str ES
network_name_str España
repository_id_str
spelling Vision models fine-tuned by cinema professionals for High Dynamic Range imaging in moviesCyriac, PraveenCanham, TrevorKane, DavidBertalmío, MarceloHigh dynamic rangeVision modelsVisual perceptionTone mappingInverse tone mappingCinema post-productionMany challenges that deal with processing of HDR material remain very much open for the film industry, whose extremely demanding quality standards are not met by existing automatic methods. Therefore, when dealing with HDR content, substantial work by very skilled technicians has to be carried out at every step of the movie production chain. Based on recent findings and models from vision science, we propose in this work effective tone mapping and inverse tone mapping algorithms for production, post-production and exhibition. These methods are automatic and real-time, and they have been both fine-tuned and validated by cinema professionals, with psychophysical tests demonstrating that the proposed algorithms outperform both the academic and industrial state-of-the-art. We believe these methods bring the field closer to having fully automated solutions for important challenges for the cinema industry that are currently solved manually or sub-optimally. Another contribution of our research is to highlight the limitations of existing image quality metrics when applied to the tone mapping problem, as none of them, including two state-of-the-art deep learning metrics for image perception, are able to predict the preferences of the observers.This work has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement number 761544 (project HDR4EU) and under grant agreement number 780470 (project SAUCE), and by the Spanish government and FEDER Fund, grant ref. PGC2018-099651-B-I00 (MCIU/AEI/FEDER, UE). We’re very grateful to Albert Pascual, Brett Harrison, Stephane Cattan and everyone at Deluxe-Spain, Alejandro Matus and everyone at Moonlight Barcelona, for their help in fine-tuning and validating our method.Springer202020202020info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfapplication/pdfhttp://hdl.handle.net/10230/45415http://dx.doi.org/10.1007/s11042-020-09532-yreponame:Repositorio Digital de la UPFinstname:Universitat Pompeu FabraInglésMultimedia Tools and Applications. 2020 Sep 15;80:2537–63info:eu-repo/grantAgreement/EC/H2020/761544info:eu-repo/grantAgreement/EC/H2020/780470info:eu-repo/grantAgreement/ES/2PE/PGC2018-099651-B-I00This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.http://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:repositori.upf.edu:10230/454152026-06-12T07:21:37Z
dc.title.none.fl_str_mv Vision models fine-tuned by cinema professionals for High Dynamic Range imaging in movies
title Vision models fine-tuned by cinema professionals for High Dynamic Range imaging in movies
spellingShingle Vision models fine-tuned by cinema professionals for High Dynamic Range imaging in movies
Cyriac, Praveen
High dynamic range
Vision models
Visual perception
Tone mapping
Inverse tone mapping
Cinema post-production
title_short Vision models fine-tuned by cinema professionals for High Dynamic Range imaging in movies
title_full Vision models fine-tuned by cinema professionals for High Dynamic Range imaging in movies
title_fullStr Vision models fine-tuned by cinema professionals for High Dynamic Range imaging in movies
title_full_unstemmed Vision models fine-tuned by cinema professionals for High Dynamic Range imaging in movies
title_sort Vision models fine-tuned by cinema professionals for High Dynamic Range imaging in movies
dc.creator.none.fl_str_mv Cyriac, Praveen
Canham, Trevor
Kane, David
Bertalmío, Marcelo
author Cyriac, Praveen
author_facet Cyriac, Praveen
Canham, Trevor
Kane, David
Bertalmío, Marcelo
author_role author
author2 Canham, Trevor
Kane, David
Bertalmío, Marcelo
author2_role author
author
author
dc.subject.none.fl_str_mv High dynamic range
Vision models
Visual perception
Tone mapping
Inverse tone mapping
Cinema post-production
topic High dynamic range
Vision models
Visual perception
Tone mapping
Inverse tone mapping
Cinema post-production
description Many challenges that deal with processing of HDR material remain very much open for the film industry, whose extremely demanding quality standards are not met by existing automatic methods. Therefore, when dealing with HDR content, substantial work by very skilled technicians has to be carried out at every step of the movie production chain. Based on recent findings and models from vision science, we propose in this work effective tone mapping and inverse tone mapping algorithms for production, post-production and exhibition. These methods are automatic and real-time, and they have been both fine-tuned and validated by cinema professionals, with psychophysical tests demonstrating that the proposed algorithms outperform both the academic and industrial state-of-the-art. We believe these methods bring the field closer to having fully automated solutions for important challenges for the cinema industry that are currently solved manually or sub-optimally. Another contribution of our research is to highlight the limitations of existing image quality metrics when applied to the tone mapping problem, as none of them, including two state-of-the-art deep learning metrics for image perception, are able to predict the preferences of the observers.
publishDate 2020
dc.date.none.fl_str_mv 2020
2020
2020
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10230/45415
http://dx.doi.org/10.1007/s11042-020-09532-y
url http://hdl.handle.net/10230/45415
http://dx.doi.org/10.1007/s11042-020-09532-y
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv Multimedia Tools and Applications. 2020 Sep 15;80:2537–63
info:eu-repo/grantAgreement/EC/H2020/761544
info:eu-repo/grantAgreement/EC/H2020/780470
info:eu-repo/grantAgreement/ES/2PE/PGC2018-099651-B-I00
dc.rights.none.fl_str_mv http://creativecommons.org/licenses/by/4.0/
info:eu-repo/semantics/openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
dc.source.none.fl_str_mv reponame:Repositorio Digital de la UPF
instname:Universitat Pompeu Fabra
instname_str Universitat Pompeu Fabra
reponame_str Repositorio Digital de la UPF
collection Repositorio Digital de la UPF
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869414328492359680
score 15.811543

Registros relacionados