Joint large displacement scene flow and occlusion variational estimation

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Palomares, Roberto P.
• dc.contributor.author Haro Ortega, Gloria
• dc.contributor.author Ballester, Coloma
• dc.date.accessioned 2018-11-22T09:23:51Z
• dc.date.available 2018-11-22T09:23:51Z
• dc.date.issued 2017
• dc.description Comunicació presentada al congrés International Conference on Computer Vision Theory and Applications (VISSAP) celebrat a Porto (Portugal) del 27 de febrer a l'1 de març de 2017.
• dc.description.abstract This paper presents a novel variational approach for the joint estimation of scene flow and occlusions. Our method does not assume that a depth sensor is available. Instead, we use a stereo sequence and exploit the fact that points that are occluded in time, might be visible from the other view and thus the 3D geometry can be densely reinforced in an appropriate manner through a simultaneous motion occlusion characterization. Moreover, large displacements are correctly captured thanks to an optimization strategy that uses a set of sparse image correspondences to guide the minimization process. We include qualitative and quantitative experimental results on several datasets illustrating that both proposals help to improve the baseline results.
• dc.description.sponsorship The authors acknowledge partial support by TIN2015-70410-C2-1-R (MINECO/FEDER, UE) and by GRC reference 2014 SGR 1301, Generalitat de Catalunya.
• dc.format.mimetype application/pdf
• dc.identifier.citation Palomares RP, Haro G, Ballester C. Joint large displacement scene flow and occlusion variational estimation. In: Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2017); 2017 Feb 27 - Mar 1; Porto, Portugal. Setúbal: Scitepress; 2017. p. 172-80. DOI: 10.5220/0006110601720180
• dc.identifier.doi http://dx.doi.org/10.5220/0006110601720180
• dc.identifier.isbn 978-989-758-227-1
• dc.identifier.uri http://hdl.handle.net/10230/35823
• dc.language.iso eng
• dc.publisher SCITEPRESS – Science and Technology Publications, Lda.
• dc.relation.ispartof Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2017); 2017 Feb 27 - Mar 1; Porto, Portugal. Setúbal: Scitepress; 2017.
• dc.relation.projectID info:eu-repo/grantAgreement/ES/1PE/TIN2015-70410-C2-1-R
• dc.rights © 2017 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.subject.keyword Scene flow
• dc.subject.keyword Variational methods
• dc.subject.keyword Coordinate descent
• dc.subject.keyword Sparse matches
• dc.title Joint large displacement scene flow and occlusion variational estimation
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/publishedVersion