A rotation-invariant regularization term for optical flow related problems

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 2021-03-05T07:16:07Z
  • dc.date.available 2021-03-05T07:16:07Z
  • dc.date.issued 2014
  • dc.description Comunicació presentada al 12th Asian Conference on Computer Vision (ACCV 2014), celebrat de l'1 al 5 de novembre de 2014 a Singapur.
  • dc.description.abstract This paper proposes a new regularization term for optical flow related problems. The proposed regularizer properly handles rotation movements and it also produces good smoothness conditions on the flow field while preserving discontinuities. We also present a dual formulation of the new term that turns the minimization problem into a saddle-point problem that can be solved using a primal-dual algorithm. The performance of the new regularizer has been compared against the Total Variation (TV) in three different problems: optical flow estimation, optical flow inpainting, and optical flow completion from sparse samples. In the three situations the new regularizer improves the results obtained with the TV as a smoothing term.en
  • dc.description.sponsorship We acknowledge partial support by MICINN project, reference MTM2012-30772, by GRC reference 2009 SGR 773 funded by the Generalitat de Catalunya, and by the ERC Advanced Grant INPAINTING (Grant agreement no.: 319899). The second author acknowledges partial support to the Ramón y Cajal program of the MINECO.
  • dc.format.mimetype application/pdf
  • dc.identifier.citation Palomares RP, Haro G, Ballester C. A rotation-invariant regularization term for optical flow related problems. In: Cremers D, Reid I, Saito H, Yang MH. Lecture Notes in Computer Science. 12th Asian Conference on Computer Vision (ACCV 2014); 2014 Nov 1-5; Singapore, Singapore. Cham: Springer; 2014. p. 304-19. DOI: 10.1007/978-3-319-16814-2_20
  • dc.identifier.doi http://dx.doi.org/10.1007/978-3-319-16814-2_20
  • dc.identifier.uri http://hdl.handle.net/10230/46667
  • dc.language.iso eng
  • dc.publisher Springer
  • dc.relation.ispartof Cremers D, Reid I, Saito H, Yang MH. Lecture Notes in Computer Science. 12th Asian Conference on Computer Vision (ACCV 2014); 2014 Nov 1-5; Singapore, Singapore. Cham: Springer; 2014. p. 304-19
  • dc.relation.projectID info:eu-repo/grantAgreement/ES/3PN/MTM2012-30772
  • dc.relation.projectID info:eu-repo/grantAgreement/EC/FP7/319899
  • dc.rights © Springer The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-16814-2_20
  • dc.rights.accessRights info:eu-repo/semantics/openAccess
  • dc.subject.keyword Optical flowen
  • dc.subject.keyword Proposed regularization termen
  • dc.subject.keyword Sparse samplingen
  • dc.subject.keyword Motion Inpaintingen
  • dc.subject.keyword Ground truth optical flowen
  • dc.title A rotation-invariant regularization term for optical flow related problemsen
  • dc.type info:eu-repo/semantics/conferenceObject
  • dc.type.version info:eu-repo/semantics/acceptedVersion

Col·leccions

Congressos (Departament de Tecnologies de la Informació i les Comunicacions)
Documents OpenAIRE (Open Access Infrastructure for Research in Europe)