A majorization–minimization-based method for nonconvex inverse rig problems in facial animation

Bibliographic Details
Main Author: Racković, Stevo
Publication Date: 2024
Other Authors: Soares, Cláudia, Jakovetić, Dušan, Desnica, Zoranka
Format: Article
Language: eng
Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
Download full: http://hdl.handle.net/10362/164432
Summary: This work has received funding from the European Union’s Horizon 2020 research and innovation program under the Marie Skłodowska-Curie grant agreement No. 812912, from FCT IP strategic project NOVA LINCS (FCT UIDB/04516/2020) and project DSAIPA/AI/0087/2018. The work has also been supported in part by the Ministry of Education, Science and Technological Development of the Republic of Serbia (Grant No. 451-03-9/2021-14/200125) and Provincial Secretariat for Higher Education and Scientific Research (Grant No. 142-451-2593/2021-01/2). Funding Open access funding provided by FCT|FCCN (b-on). Publisher Copyright: © 2023, The Author(s).
id RCAP_29021d4a849bdeb20af57d0e100a8773
oai_identifier_str oai:run.unl.pt:10362/164432
network_acronym_str RCAP
network_name_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository_id_str https://opendoar.ac.uk/repository/7160
spelling A majorization–minimization-based method for nonconvex inverse rig problems in facial animationalgorithm derivationInverse rigMajorization–MinimizationQuadratic blendshape modelBusiness, Management and Accounting (miscellaneous)Control and OptimizationThis work has received funding from the European Union’s Horizon 2020 research and innovation program under the Marie Skłodowska-Curie grant agreement No. 812912, from FCT IP strategic project NOVA LINCS (FCT UIDB/04516/2020) and project DSAIPA/AI/0087/2018. The work has also been supported in part by the Ministry of Education, Science and Technological Development of the Republic of Serbia (Grant No. 451-03-9/2021-14/200125) and Provincial Secretariat for Higher Education and Scientific Research (Grant No. 142-451-2593/2021-01/2). Funding Open access funding provided by FCT|FCCN (b-on). Publisher Copyright: © 2023, The Author(s).Automated methods for facial animation are a necessary tool in the modern industry since the standard blendshape head models consist of hundreds of controllers, and a manual approach is painfully slow. Different solutions have been proposed that produce output in real-time or generalize well for different face topologies. However, all these prior works consider a linear approximation of the blendshape function and hence do not provide a high-enough level of detail for modern realistic human face reconstruction. A second-order blendshape approximation leads to higher fidelity facial animation but generates a non-linear least squares optimization problem with high dimensionality. We derive a method for solving the inverse rig in blendshape animation using quadratic corrective terms, which increases accuracy. At the same time, due to the proposed construction of the objective function, it yields a sparser estimated weight vector compared to the state-of-the-art methods. The former feature means lower demand for subsequent manual corrections of the solution, while the latter indicates that the manual modifications are also easier to include. Our algorithm is iterative and employs a Majorization–Minimization paradigm to cope with the increased complexity produced by adding corrective terms. The surrogate function is easy to solve and allows for further parallelization on the component level within each iteration. This paper is complementary to an accompanying paper (Racković et al. arxiv preprint. https://arxiv.org/abs/2302.04843 , 2023) where we provide detailed experimental results and discussion, including highly-realistic animation data, and show a clear superiority of the results compared to the state-of-the-art methods.DI - Departamento de InformáticaRUNRacković, StevoSoares, CláudiaJakovetić, DušanDesnica, Zoranka2024-03-05T00:16:05Z2024-032024-03-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article15application/pdfhttp://hdl.handle.net/10362/164432eng1862-4472PURE: 84311299https://doi.org/10.1007/s11590-023-02012-winfo:eu-repo/semantics/openAccessreponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiainstacron:RCAAP2024-05-22T18:19:04Zoai:run.unl.pt:10362/164432Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireinfo@rcaap.ptopendoar:https://opendoar.ac.uk/repository/71602025-05-28T17:49:45.603970Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiafalse
dc.title.none.fl_str_mv A majorization–minimization-based method for nonconvex inverse rig problems in facial animation
algorithm derivation
title A majorization–minimization-based method for nonconvex inverse rig problems in facial animation
spellingShingle A majorization–minimization-based method for nonconvex inverse rig problems in facial animation
Racković, Stevo
Inverse rig
Majorization–Minimization
Quadratic blendshape model
Business, Management and Accounting (miscellaneous)
Control and Optimization
title_short A majorization–minimization-based method for nonconvex inverse rig problems in facial animation
title_full A majorization–minimization-based method for nonconvex inverse rig problems in facial animation
title_fullStr A majorization–minimization-based method for nonconvex inverse rig problems in facial animation
title_full_unstemmed A majorization–minimization-based method for nonconvex inverse rig problems in facial animation
title_sort A majorization–minimization-based method for nonconvex inverse rig problems in facial animation
author Racković, Stevo
author_facet Racković, Stevo
Soares, Cláudia
Jakovetić, Dušan
Desnica, Zoranka
author_role author
author2 Soares, Cláudia
Jakovetić, Dušan
Desnica, Zoranka
author2_role author
author
author
dc.contributor.none.fl_str_mv DI - Departamento de Informática
RUN
dc.contributor.author.fl_str_mv Racković, Stevo
Soares, Cláudia
Jakovetić, Dušan
Desnica, Zoranka
dc.subject.por.fl_str_mv Inverse rig
Majorization–Minimization
Quadratic blendshape model
Business, Management and Accounting (miscellaneous)
Control and Optimization
topic Inverse rig
Majorization–Minimization
Quadratic blendshape model
Business, Management and Accounting (miscellaneous)
Control and Optimization
description This work has received funding from the European Union’s Horizon 2020 research and innovation program under the Marie Skłodowska-Curie grant agreement No. 812912, from FCT IP strategic project NOVA LINCS (FCT UIDB/04516/2020) and project DSAIPA/AI/0087/2018. The work has also been supported in part by the Ministry of Education, Science and Technological Development of the Republic of Serbia (Grant No. 451-03-9/2021-14/200125) and Provincial Secretariat for Higher Education and Scientific Research (Grant No. 142-451-2593/2021-01/2). Funding Open access funding provided by FCT|FCCN (b-on). Publisher Copyright: © 2023, The Author(s).
publishDate 2024
dc.date.none.fl_str_mv 2024-03-05T00:16:05Z
2024-03
2024-03-01T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/164432
url http://hdl.handle.net/10362/164432
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 1862-4472
PURE: 84311299
https://doi.org/10.1007/s11590-023-02012-w
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 15
application/pdf
dc.source.none.fl_str_mv reponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron:RCAAP
instname_str FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron_str RCAAP
institution RCAAP
reponame_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
collection Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository.name.fl_str_mv Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
repository.mail.fl_str_mv info@rcaap.pt
_version_ 1833596994742910976

Similar Items