Mostra el registre d'ítem simple

dc.contributor.authorAgudo Martínez, Antonio
dc.contributor.authorMoreno-Noguer, Francesc
dc.contributor.otherInstitut de Robòtica i Informàtica Industrial
dc.date.accessioned2020-02-17T15:24:58Z
dc.date.available2020-02-17T15:24:58Z
dc.date.issued2019
dc.identifier.citationAgudo, A.; Moreno-Noguer, F. Shape basis interpretation for monocular deformable 3D reconstruction. "IEEE transactions on multimedia", 2019, vol. 21, núm. 4, p. 821-834.
dc.identifier.issn1520-9210
dc.identifier.urihttp://hdl.handle.net/2117/177861
dc.description© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
dc.description.abstractIn this paper, we propose a novel interpretable shape model to encode object non-rigidity. We first use the initial frames of a monocular video to recover a rest shape, used later to compute a dissimilarity measure based on a distance matrix measurement. Spectral analysis is then applied to this matrix to obtain a reduced shape basis, that in contrast to existing approaches, can be physically interpreted. In turn, these pre-computed shape bases are used to linearly span the deformation of a wide variety of objects. We introduce the low-rank basis into a sequential approach to recover both camera motion and non-rigid shape from the monocular video, by simply optimizing the weights of the linear combination using bundle adjustment. Since the number of parameters to optimize per frame is relatively small, specially when physical priors are considered, our approach is fast and can potentially run in real time. Validation is done in a wide variety of real-world objects, undergoing both inextensible and extensible deformations. Our approach achieves remarkable robustness to artifacts such as noisy and missing measurements and shows an improved performance to competing methods.
dc.format.extent14 p.
dc.language.isoeng
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 Spain
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subjectÀrees temàtiques de la UPC::Informàtica::Automàtica i control
dc.subject.otherDeformable Shape Analysis
dc.subject.otherDynamic Modeling
dc.subject.otherStructure from Motion
dc.subject.otherLow-Rank Representation
dc.subject.otherOptimization
dc.titleShape basis interpretation for monocular deformable 3D reconstruction
dc.typeArticle
dc.contributor.groupUniversitat Politècnica de Catalunya. ROBiri - Grup de Robòtica de l'IRI
dc.identifier.doi10.1109/TMM.2018.2870081
dc.description.peerreviewedPeer Reviewed
dc.subject.inspecClassificació INSPEC::Optimisation
dc.relation.publisherversionhttps://ieeexplore.ieee.org/document/8466043
dc.rights.accessOpen Access
local.identifier.drac24902755
dc.description.versionPostprint (author's final draft)
dc.relation.projectidinfo:eu-repo/grantAgreement/MINECO/2PE/MDM-2016-0656
dc.relation.projectidinfo:eu-repo/grantAgreement/EC/FP7/231724/EU/HUman behavioral Modeling for enhancing learning by Optimizing hUman-Robot interaction/HUMOUR
local.citation.authorAgudo, A.; Moreno-Noguer, F.
local.citation.publicationNameIEEE transactions on multimedia
local.citation.volume21
local.citation.number4
local.citation.startingPage821
local.citation.endingPage834


Fitxers d'aquest items

Thumbnail

Aquest ítem apareix a les col·leccions següents

Mostra el registre d'ítem simple