English   español  
Please use this identifier to cite or link to this item: http://hdl.handle.net/10261/166698
Share/Impact:
Statistics
logo share SHARE logo core CORE   Add this article to your Mendeley library MendeleyBASE

Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE
Exportar a otros formatos:

DC FieldValueLanguage
dc.contributor.authorAgudo, Antonio-
dc.contributor.authorMoreno-Noguer, Francesc-
dc.date.accessioned2018-06-20T10:06:25Z-
dc.date.available2018-06-20T10:06:25Z-
dc.date.issued2017-
dc.identifierdoi: 10.1007/s11263-016-0972-8-
dc.identifiere-issn: 1573-1405-
dc.identifierissn: 0920-5691-
dc.identifier.citationInternational Journal of Computer Vision 122(2): 371-387 (2017)-
dc.identifier.urihttp://hdl.handle.net/10261/166698-
dc.description.abstractIn this paper, we simultaneously estimate camera pose and non-rigid 3D shape from a monocular video, using a sequential solution that combines local and global representations. We model the object as an ensemble of particles, each ruled by the linear equation of the Newton’s second law of motion. This dynamic model is incorporated into a bundle adjustment framework, in combination with simple regularization components that ensure temporal and spatial consistency. The resulting approach allows to sequentially estimate shape and camera poses, while progressively learning a global low-rank model of the shape that is fed back into the optimization scheme, introducing thus, global constraints. The overall combination of local (physical) and global (statistical) constraints yields a solution that is both efficient and robust to several artifacts such as noisy and missing data or sudden camera motions, without requiring any training data at all. Validation is done in a variety of real application domains, including articulated and non-rigid motion, both for continuous and discontinuous shapes. Our on-line methodology yields significantly more accurate reconstructions than competing sequential approaches, being even comparable to the more computationally demanding batch methods.-
dc.description.sponsorshipThis work has been partially supported by the Spanish Ministry of Science and Innovation under project RobInstruct TIN2014-58178-R; by a scholarship FPU12/04886 from the Spanish MECD; and by the ERA-net CHISTERA projects VISEN PCIN-2013-047 and I-DRESS PCIN-2015-147.-
dc.publisherSpringer Nature-
dc.relationMINECO/ICTI2013-2016/TIN2014-58178-R-
dc.relationMINECO/ICTI2013-2016/PCIN-2013-047-
dc.relationMINECO/ICTI2013-2016/PCIN-2015-147-
dc.relation.isversionofPostprint-
dc.rightsopenAccess-
dc.subjectLow-rank models-
dc.subjectSequential non-rigid structure from motion-
dc.subjectParticle dynamics-
dc.subjectBundle adjustment-
dc.titleCombining local-physical and global-statistical models for sequential deformable shape from motion-
dc.typeartículo-
dc.identifier.doihttp://dx.doi.org/10.1007/s11263-016-0972-8-
dc.relation.publisherversionhttps://doi.org/10.1007/s11263-016-0972-8-
dc.date.updated2018-06-20T10:06:25Z-
dc.description.versionPeer Reviewed-
dc.language.rfc3066eng-
dc.contributor.funderMinisterio de Educación, Cultura y Deporte (España)-
dc.contributor.funderMinisterio de Economía y Competitividad (España)-
dc.contributor.funderMinisterio de Ciencia e Innovación (España)-
dc.relation.csic-
dc.identifier.funderhttp://dx.doi.org/10.13039/501100004837es_ES
dc.identifier.funderhttp://dx.doi.org/10.13039/501100003176es_ES
dc.identifier.funderhttp://dx.doi.org/10.13039/501100003329es_ES
Appears in Collections:(IRII) Artículos
Files in This Item:
File Description SizeFormat 
combinmotion.pdf4,81 MBAdobe PDFThumbnail
View/Open
Show simple item record
 


WARNING: Items in Digital.CSIC are protected by copyright, with all rights reserved, unless otherwise indicated.