Show simple item record

dc.contributor.authorSmolic, Aljosa
dc.date.accessioned2021-02-13T10:56:21Z
dc.date.available2021-02-13T10:56:21Z
dc.date.created6-11 June 2021en
dc.date.issued2021
dc.date.submitted2021en
dc.identifier.citationEgan, D., Alain, M., Smolic, A., Light field style transfer with local angular consistency, 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),, Toronto, Canada, 6-11 June 2021en
dc.identifier.otherN
dc.description.abstractStyle transfer involves combining the style of one image with the content of another to form a new image. Unlike traditional two-dimensional images which only capture the spatial intensity of light rays, four-dimensional light fields also capture the angular direction of the light rays. Thus, applying style transfer to a light field requires to not only render convincing style transfer for each view, but also to preserve its angular structure. We present a novel optimization-based method for light field style transfer which iteratively propagates the style transfer from the centre view towards the outer views while enforcing local angular consistency. For this purpose, a new initialisation method and angular loss function is proposed for the optimization process. In addition, since style transfer for light field is an emerging topic, no clear evaluation procedure is available. Thus, we investigate the use of a recently proposed metric designed to evaluate light field angular consistency, as well as a proposed variant.en
dc.format.extent1-5en
dc.language.isoenen
dc.relation.urihttps://v-sense.scss.tcd.ie/wp-content/uploads/2021/02/Neural_Style_Transfer_for_Light_Field.pdfen
dc.rightsYen
dc.subjectLight fielden
dc.subjectStyle transferen
dc.titleLight field style transfer with local angular consistencyen
dc.title.alternative2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),en
dc.typeConference Paperen
dc.type.supercollectionscholarly_publicationsen
dc.identifier.peoplefinderurlhttp://people.tcd.ie/smolica
dc.identifier.rssinternalid223712
dc.rights.ecaccessrightsopenAccess
dc.relation.citesCitesen
dc.subject.TCDThemeCreative Technologiesen
dc.subject.TCDThemeDigital Engagementen
dc.subject.TCDTagComputer Education/Literacyen
dc.subject.TCDTagData Analysisen
dc.subject.TCDTagMultimedia & Creativityen
dc.subject.TCDTagSignal Processingen
dc.identifier.rssurihttps://v-sense.scss.tcd.ie/wp-content/uploads/2021/02/Neural_Style_Transfer_for_Light_Field.pdf
dc.subject.darat_impairmentOtheren
dc.status.accessibleNen
dc.contributor.sponsorScience Foundation Ireland (SFI)en
dc.contributor.sponsorGrantNumber15/RP/2776en
dc.identifier.urihttp://hdl.handle.net/2262/95103


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record