Detailed 3D face reconstruction from a single RGB image

This paper introduces a method to obtain a detailed 3D reconstruction of facial skin from a single RGB image. To this end, we propose the exclusive use of an input image without requiring any information about the observed material nor training data to model the wrinkle properties. They are detected...

Full description

Bibliographic Details
Authors: Rotger, Gemma, Moreno-Noguer, Francesc, Lumbreras, Felipe, Agudo Martínez, Antonio
Format: article
Status:Versión aceptada para publicación
Publication Date:2019
Country:España
Institution:Consejo Superior de Investigaciones Científicas (CSIC)
Repository:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/206679
Online Access:http://hdl.handle.net/10261/206679
Access Level:Open access
Keyword:3D Wrinkle Reconstruction
Face Analysis
Optimization
id ES_aa1db3f4df95ca8454754ba2ee7aa86c
oai_identifier_str oai:digital.csic.es:10261/206679
network_acronym_str ES
network_name_str España
repository_id_str
spelling Detailed 3D face reconstruction from a single RGB imageRotger, GemmaMoreno-Noguer, FrancescLumbreras, FelipeAgudo Martínez, Antonio3D Wrinkle ReconstructionFace AnalysisOptimizationThis paper introduces a method to obtain a detailed 3D reconstruction of facial skin from a single RGB image. To this end, we propose the exclusive use of an input image without requiring any information about the observed material nor training data to model the wrinkle properties. They are detected and characterized directly from the image via a simple and effective parametric model, determining several features such as location, orientation, width, and height. With these ingredients, we propose to minimize a photometric error to retrieve the final detailed 3D map, which is initialized by current techniques based on deep learning. In contrast with other approaches, we only require estimating a depth parameter, making our approach fast and intuitive. Extensive experimental evaluation is presented in a wide variety of synthetic and real images, including different skin properties and facial expressions. In all cases, our method outperforms the current approaches regarding 3D reconstruction accuracy, providing striking results for both large and fine wrinkles.This work has been partially supported by the Spanish Ministry of Science and Innovation under projects FireDMMI TIN2014-56919-C3-2- R, BOSSS TIN2017-89723-P, and HuMoUR TIN2017- 90086-R; by the CSIC project R3OBJ 201850I099, and by the Spanish State Research Agency through the María de Maeztu Seal of Excellence to IRI MDM2016-0656.University of West BohemiaMinisterio de Economía y Competitividad (España)Ministerio de Ciencia, Innovación y Universidades (España)Agencia Estatal de Investigación (España)Consejo Superior de Investigaciones Científicas (España)Consejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]2020202020192020info:eu-repo/semantics/articlehttp://purl.org/coar/resource_type/c_6501Postprintinfo:eu-repo/semantics/acceptedVersionhttp://hdl.handle.net/10261/206679reponame:DIGITAL.CSIC. Repositorio Institucional del CSICinstname:Consejo Superior de Investigaciones Científicas (CSIC)Inglés#PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE##PLACEHOLDER_PARENT_METADATA_VALUE#info:eu-repo/grantAgreement/MINECO/Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016/TIN2014-56919-C3-2-Rinfo:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/TIN2017-89723-PTIN2017-89723-P/AEI/10.13039/501100011033info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/TIN2017-90086-RTIN2017-90086-R/AEI/10.13039/501100011033info:eu-repo/grantAgreement/MINECO/Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016/MDM-2016-0656http://dx.doi.org/10.24132/JWSCG.2019.27.2.3Síinfo:eu-repo/semantics/openAccessoai:digital.csic.es:10261/2066792026-05-22T06:33:51Z
dc.title.none.fl_str_mv Detailed 3D face reconstruction from a single RGB image
title Detailed 3D face reconstruction from a single RGB image
spellingShingle Detailed 3D face reconstruction from a single RGB image
Rotger, Gemma
3D Wrinkle Reconstruction
Face Analysis
Optimization
title_short Detailed 3D face reconstruction from a single RGB image
title_full Detailed 3D face reconstruction from a single RGB image
title_fullStr Detailed 3D face reconstruction from a single RGB image
title_full_unstemmed Detailed 3D face reconstruction from a single RGB image
title_sort Detailed 3D face reconstruction from a single RGB image
dc.creator.none.fl_str_mv Rotger, Gemma
Moreno-Noguer, Francesc
Lumbreras, Felipe
Agudo Martínez, Antonio
author Rotger, Gemma
author_facet Rotger, Gemma
Moreno-Noguer, Francesc
Lumbreras, Felipe
Agudo Martínez, Antonio
author_role author
author2 Moreno-Noguer, Francesc
Lumbreras, Felipe
Agudo Martínez, Antonio
author2_role author
author
author
dc.contributor.none.fl_str_mv Ministerio de Economía y Competitividad (España)
Ministerio de Ciencia, Innovación y Universidades (España)
Agencia Estatal de Investigación (España)
Consejo Superior de Investigaciones Científicas (España)
Consejo Superior de Investigaciones Científicas [https://ror.org/02gfc7t72]
dc.subject.none.fl_str_mv 3D Wrinkle Reconstruction
Face Analysis
Optimization
topic 3D Wrinkle Reconstruction
Face Analysis
Optimization
description This paper introduces a method to obtain a detailed 3D reconstruction of facial skin from a single RGB image. To this end, we propose the exclusive use of an input image without requiring any information about the observed material nor training data to model the wrinkle properties. They are detected and characterized directly from the image via a simple and effective parametric model, determining several features such as location, orientation, width, and height. With these ingredients, we propose to minimize a photometric error to retrieve the final detailed 3D map, which is initialized by current techniques based on deep learning. In contrast with other approaches, we only require estimating a depth parameter, making our approach fast and intuitive. Extensive experimental evaluation is presented in a wide variety of synthetic and real images, including different skin properties and facial expressions. In all cases, our method outperforms the current approaches regarding 3D reconstruction accuracy, providing striking results for both large and fine wrinkles.
publishDate 2019
dc.date.none.fl_str_mv 2019
2020
2020
2020
dc.type.none.fl_str_mv info:eu-repo/semantics/article
http://purl.org/coar/resource_type/c_6501
Postprint
info:eu-repo/semantics/acceptedVersion
format article
status_str acceptedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10261/206679
url http://hdl.handle.net/10261/206679
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv #PLACEHOLDER_PARENT_METADATA_VALUE#
#PLACEHOLDER_PARENT_METADATA_VALUE#
#PLACEHOLDER_PARENT_METADATA_VALUE#
#PLACEHOLDER_PARENT_METADATA_VALUE#
#PLACEHOLDER_PARENT_METADATA_VALUE#
#PLACEHOLDER_PARENT_METADATA_VALUE#
info:eu-repo/grantAgreement/MINECO/Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016/TIN2014-56919-C3-2-R
info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/TIN2017-89723-P
TIN2017-89723-P/AEI/10.13039/501100011033
info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/TIN2017-90086-R
TIN2017-90086-R/AEI/10.13039/501100011033
info:eu-repo/grantAgreement/MINECO/Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016/MDM-2016-0656
http://dx.doi.org/10.24132/JWSCG.2019.27.2.3
Sí
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv University of West Bohemia
publisher.none.fl_str_mv University of West Bohemia
dc.source.none.fl_str_mv reponame:DIGITAL.CSIC. Repositorio Institucional del CSIC
instname:Consejo Superior de Investigaciones Científicas (CSIC)
instname_str Consejo Superior de Investigaciones Científicas (CSIC)
reponame_str DIGITAL.CSIC. Repositorio Institucional del CSIC
collection DIGITAL.CSIC. Repositorio Institucional del CSIC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869416134851166208
score 15,81155

Similar Items