On anisotropic optical flow inpainting algorithms

dc.contributor.authorRaad, Lara
dc.contributor.authorOliver Parera, Maria
dc.contributor.authorBallester, Coloma
dc.contributor.authorHaro Ortega, Gloria
dc.contributor.authorMeinhardt Llopis, Enric
dc.date.accessioned2020-09-02T07:09:41Z
dc.date.available2020-09-02T07:09:41Z
dc.date.issued2020
dc.description.abstractThis work describes two anisotropic optical flow inpainting algorithms. The first one recovers the missing flow values using the Absolutely Minimizing Lipschitz Extension partial differential equation (also called infinity Laplacian equation) and the second one uses the Laplace partial differential equation, both defined on a Riemmanian manifold. The Riemannian manifold is defined by endowing the plane domain with an appropriate metric depending on the reference video frame. A detailed analysis of both approaches is provided and their results are compared on three different applications: flow densification, occlusion inpainting and large hole inpainting.en
dc.format.mimetypeapplication/pdf
dc.identifier.citationRaad L, Oliver M, Ballester C, Haro G, Meinhardt E. On anisotropic optical flow inpainting algorithms. Image Processing On Line Journal. 2020;10:78-104. DOI: 10.5201/ipol.2020.281
dc.identifier.doihttps://doi.org/10.5201/ipol.2020.281
dc.identifier.issn2105–1232
dc.identifier.urihttp://hdl.handle.net/10230/45244
dc.language.isoeng
dc.publisherIPOL
dc.relation.ispartofImage Processing On Line Journal. 2020;10:78-104.
dc.relation.projectIDinfo:eu-repo/grantAgreement/EC/H2020/777826
dc.rights© 2020 IPOL & the authors. The article is distributed under a Creative Commons CC-BY-NC-SA license.
dc.rights.accessRightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttps://creativecommons.org/licenses/by-nc-sa/3.0/
dc.subject.keywordOptical flow inpaintingen
dc.subject.keywordAbsolutely minimizing Lipschitz extensionen
dc.subject.keywordLaplace-Beltramien
dc.titleOn anisotropic optical flow inpainting algorithms
dc.typeinfo:eu-repo/semantics/article
dc.type.versioninfo:eu-repo/semantics/publishedVersion

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
raad_ipol_anis.pdf
Size:
16.6 MB
Format:
Adobe Portable Document Format

License

Rights