Motion inpainting by an image-based geodesic AMLE method

Mostra el registre complet Registre parcial de l'ítem

  • dc.contributor.author Oliver, Maria
  • dc.contributor.author Raad, Lara
  • dc.contributor.author Ballester, Coloma
  • dc.contributor.author Haro Ortega, Gloria
  • dc.date.accessioned 2018-11-22T08:34:29Z
  • dc.date.available 2018-11-22T08:34:29Z
  • dc.date.issued 2018
  • dc.description Comunicació presentada al congrés 25th IEEE International Conference on Image Processing (ICIP) celebrat del 7 al 10 d'octubre de 2018 a Atenes, Grècia.
  • dc.description.abstract This work presents an automatic method for optical flow inpainting. Given a video, each frame domain is endowed with a Riemannian metric based on the video pixel values. The missing optical flow is recovered by solving the Absolutely Minimizing Lipschitz Extension (AMLE) partial differential equation on the Riemannian manifold. An efficient numerical algorithm is proposed using eikonal operators for nonlinear elliptic partial differential equations on a finite graph. The choice of the metric is discussed and the method is applied to optical flow inpainting and sparse-to-dense optical flow estimation, achieving top-tier performance in terms of End-Point-Error (EPE).
  • dc.description.sponsorship This work is partially supported by MINECO/FEDER UE project, with reference TIN2015-70410-C2-1-R and by RISE project NoMADS.
  • dc.format.mimetype application/pdf
  • dc.identifier.citation Oliver M, Raad L, Ballester C, Haro G. Motion inpainting by an image-based geodesic AMLE method. In: 2018 25th IEEE International Conference on Image Processing (ICIP); 2018 Oct 7-10; Athens, Greece. Piscataway (NJ): IEEE; 2018. p. 2267-71. DOI: 10.1109/ICIP.2018.8451851
  • dc.identifier.doi http://dx.doi.org/10.1109/ICIP.2018.8451851
  • dc.identifier.issn 2381-8549
  • dc.identifier.uri http://hdl.handle.net/10230/35820
  • dc.language.iso eng
  • dc.publisher Institute of Electrical and Electronics Engineers (IEEE)
  • dc.relation.ispartof 2018 25th IEEE International Conference on Image Processing (ICIP); 2018 Oct 7-10; Athens, Greece. Piscataway (NJ): IEEE; 2018.
  • dc.relation.projectID info:eu-repo/grantAgreement/ES/1PE/TIN2015-70410-C2-1-R
  • dc.rights © 2018 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. The final published article can be found at https://ieeexplore.ieee.org/document/8451851
  • dc.rights.accessRights info:eu-repo/semantics/openAccess
  • dc.subject.keyword Optical flow inpainting
  • dc.subject.keyword Sparse to dense methods
  • dc.subject.keyword Partial differential equations
  • dc.subject.keyword Absolute Minimal Lipschitz Extension
  • dc.subject.keyword Anisotropic methods
  • dc.title Motion inpainting by an image-based geodesic AMLE method
  • dc.type info:eu-repo/semantics/conferenceObject
  • dc.type.version info:eu-repo/semantics/acceptedVersion