dc.contributor.author | Smolic, Aljosa | |
dc.date.accessioned | 2021-02-13T10:56:21Z | |
dc.date.available | 2021-02-13T10:56:21Z | |
dc.date.created | 6-11 June 2021 | en |
dc.date.issued | 2021 | |
dc.date.submitted | 2021 | en |
dc.identifier.citation | Egan, 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 2021 | en |
dc.identifier.other | N | |
dc.description.abstract | Style 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.extent | 1-5 | en |
dc.language.iso | en | en |
dc.relation.uri | https://v-sense.scss.tcd.ie/wp-content/uploads/2021/02/Neural_Style_Transfer_for_Light_Field.pdf | en |
dc.rights | Y | en |
dc.subject | Light field | en |
dc.subject | Style transfer | en |
dc.title | Light field style transfer with local angular consistency | en |
dc.title.alternative | 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), | en |
dc.type | Conference Paper | en |
dc.type.supercollection | scholarly_publications | en |
dc.identifier.peoplefinderurl | http://people.tcd.ie/smolica | |
dc.identifier.rssinternalid | 223712 | |
dc.rights.ecaccessrights | openAccess | |
dc.relation.cites | Cites | en |
dc.subject.TCDTheme | Creative Technologies | en |
dc.subject.TCDTheme | Digital Engagement | en |
dc.subject.TCDTag | Computer Education/Literacy | en |
dc.subject.TCDTag | Data Analysis | en |
dc.subject.TCDTag | Multimedia & Creativity | en |
dc.subject.TCDTag | Signal Processing | en |
dc.identifier.rssuri | https://v-sense.scss.tcd.ie/wp-content/uploads/2021/02/Neural_Style_Transfer_for_Light_Field.pdf | |
dc.subject.darat_impairment | Other | en |
dc.status.accessible | N | en |
dc.contributor.sponsor | Science Foundation Ireland (SFI) | en |
dc.contributor.sponsorGrantNumber | 15/RP/2776 | en |
dc.identifier.uri | http://hdl.handle.net/2262/95103 | |