File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: ReCoNet: Real-time Coherent Video Style Transfer Network

TitleReCoNet: Real-time Coherent Video Style Transfer Network
Authors
KeywordsVideo style transfer
Optical flow
Real-time processing
Issue Date2019
PublisherSpringer. The Proceedings' web site is located at https://link.springer.com/book/10.1007/978-3-030-20876-9
Citation
Proceedings of the 14th Asian Conference on Computer Vision (ACCV), Perth, Australia, 2-6 December 2018. In Computer Vision – ACCV 2018, pt. 6, p. 637-653. Cham: Springer, 2019 How to Cite?
AbstractImage style transfer models based on convolutional neural networks usually suffer from high temporal inconsistency when applied to videos. Some video style transfer models have been proposed to improve temporal consistency, yet they fail to guarantee fast processing speed, nice perceptual style quality and high temporal consistency at the same time. In this paper, we propose a novel real-time video style transfer model, ReCoNet, which can generate temporally coherent style transfer videos while maintaining favorable perceptual styles. A novel luminance warping constraint is added to the temporal loss at the output level to capture luminance changes between consecutive frames and increase stylization stability under illumination effects. We also propose a novel feature-map-level temporal loss to further enhance temporal consistency on traceable objects. Experimental results indicate that our model exhibits outstanding performance both qualitatively and quantitatively.
DescriptionOral Session O6: Vision and Language, semantics, and low-level vision - no. O6-1: 523
Revised Selected Papers
Persistent Identifierhttp://hdl.handle.net/10722/271319
ISBN
Series/Report no.Lecture Notes in Computer Science (LNCS), v. 11366

 

DC FieldValueLanguage
dc.contributor.authorGao, C-
dc.contributor.authorGu, D-
dc.contributor.authorZhang, F-
dc.contributor.authorYu, Y-
dc.date.accessioned2019-06-24T01:07:33Z-
dc.date.available2019-06-24T01:07:33Z-
dc.date.issued2019-
dc.identifier.citationProceedings of the 14th Asian Conference on Computer Vision (ACCV), Perth, Australia, 2-6 December 2018. In Computer Vision – ACCV 2018, pt. 6, p. 637-653. Cham: Springer, 2019-
dc.identifier.isbn978-3-030-20875-2-
dc.identifier.urihttp://hdl.handle.net/10722/271319-
dc.descriptionOral Session O6: Vision and Language, semantics, and low-level vision - no. O6-1: 523-
dc.descriptionRevised Selected Papers-
dc.description.abstractImage style transfer models based on convolutional neural networks usually suffer from high temporal inconsistency when applied to videos. Some video style transfer models have been proposed to improve temporal consistency, yet they fail to guarantee fast processing speed, nice perceptual style quality and high temporal consistency at the same time. In this paper, we propose a novel real-time video style transfer model, ReCoNet, which can generate temporally coherent style transfer videos while maintaining favorable perceptual styles. A novel luminance warping constraint is added to the temporal loss at the output level to capture luminance changes between consecutive frames and increase stylization stability under illumination effects. We also propose a novel feature-map-level temporal loss to further enhance temporal consistency on traceable objects. Experimental results indicate that our model exhibits outstanding performance both qualitatively and quantitatively.-
dc.languageeng-
dc.publisherSpringer. The Proceedings' web site is located at https://link.springer.com/book/10.1007/978-3-030-20876-9-
dc.relation.ispartof14th Asian Conference on Computer Vision (ACCV), 2018-
dc.relation.ispartofComputer Vision – ACCV 2018-
dc.relation.ispartofseriesLecture Notes in Computer Science (LNCS), v. 11366-
dc.subjectVideo style transfer-
dc.subjectOptical flow-
dc.subjectReal-time processing-
dc.titleReCoNet: Real-time Coherent Video Style Transfer Network-
dc.typeConference_Paper-
dc.identifier.emailYu, Y: yzyu@cs.hku.hk-
dc.identifier.authorityYu, Y=rp01415-
dc.identifier.doi10.1007/978-3-030-20876-9_40-
dc.identifier.hkuros297944-
dc.identifier.volume6-
dc.identifier.spage637-
dc.identifier.epage653-
dc.publisher.placeCham-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats