File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Stroke Controllable Fast Style Transfer with Adaptive Receptive Fields

TitleStroke Controllable Fast Style Transfer with Adaptive Receptive Fields
Authors
KeywordsNeural Style Transfer
Adaptive receptive fields
Issue Date2018
PublisherSpringer.
Citation
European Conference on Computer Vision 2018 (ECCV), Munich, Germany, 8-14 September 2018. In Computer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XIII, p. 244-260 How to Cite?
AbstractThe Fast Style Transfer methods have been recently proposed to transfer a photograph to an artistic style in real-time. This task involves controlling the stroke size in the stylized results, which remains an open challenge. In this paper, we present a stroke controllable style transfer network that can achieve continuous and spatial stroke size control. By analyzing the factors that influence the stroke size, we propose to explicitly account for the receptive field and the style image scales. We propose a StrokePyramid module to endow the network with adaptive receptive fields, and two training strategies to achieve faster convergence and augment new stroke sizes upon a trained model respectively. By combining the proposed runtime control strategies, our network can achieve continuous changes in stroke sizes and produce distinct stroke sizes in different spatial regions within the same output image.
Persistent Identifierhttp://hdl.handle.net/10722/259643
ISBN
ISSN
2023 SCImago Journal Rankings: 0.606
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorJing, Y-
dc.contributor.authorLiu, Y-
dc.contributor.authorYang, Y-
dc.contributor.authorFeng, Z-
dc.contributor.authorYu, Y-
dc.contributor.authorTao, D-
dc.contributor.authorSong, M-
dc.date.accessioned2018-09-03T04:11:21Z-
dc.date.available2018-09-03T04:11:21Z-
dc.date.issued2018-
dc.identifier.citationEuropean Conference on Computer Vision 2018 (ECCV), Munich, Germany, 8-14 September 2018. In Computer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XIII, p. 244-260-
dc.identifier.isbn9783030012601-
dc.identifier.issn0302-9743-
dc.identifier.urihttp://hdl.handle.net/10722/259643-
dc.description.abstractThe Fast Style Transfer methods have been recently proposed to transfer a photograph to an artistic style in real-time. This task involves controlling the stroke size in the stylized results, which remains an open challenge. In this paper, we present a stroke controllable style transfer network that can achieve continuous and spatial stroke size control. By analyzing the factors that influence the stroke size, we propose to explicitly account for the receptive field and the style image scales. We propose a StrokePyramid module to endow the network with adaptive receptive fields, and two training strategies to achieve faster convergence and augment new stroke sizes upon a trained model respectively. By combining the proposed runtime control strategies, our network can achieve continuous changes in stroke sizes and produce distinct stroke sizes in different spatial regions within the same output image.-
dc.languageeng-
dc.publisherSpringer.-
dc.relation.ispartofComputer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XIII-
dc.subjectNeural Style Transfer-
dc.subjectAdaptive receptive fields-
dc.titleStroke Controllable Fast Style Transfer with Adaptive Receptive Fields-
dc.typeConference_Paper-
dc.identifier.emailYu, Y: yzyu@cs.hku.hk-
dc.identifier.authorityYu, Y=rp01415-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1007/978-3-030-01261-8_15-
dc.identifier.scopuseid_2-s2.0-85055574049-
dc.identifier.hkuros288481-
dc.identifier.spage244-
dc.identifier.epage260-
dc.identifier.eissn1611-3349-
dc.identifier.isiWOS:000590144600015-
dc.publisher.placeCham, Switzerland-
dc.identifier.issnl0302-9743-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats