File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Semi-Parametric Image Synthesis

TitleSemi-Parametric Image Synthesis
Authors
Issue Date2018
Citation
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2018, p. 8808-8816 How to Cite?
Abstract© 2018 IEEE. We present a semi-parametric approach to photographic image synthesis from semantic layouts. The approach combines the complementary strengths of parametric and nonparametric techniques. The nonparametric component is a memory bank of image segments constructed from a training set of images. Given a novel semantic layout at test time, the memory bank is used to retrieve photographic references that are provided as source material to a deep network. The synthesis is performed by a deep network that draws on the provided photographic material. Experiments on multiple semantic segmentation datasets show that the presented approach yields considerably more realistic images than recent purely parametric techniques.
Persistent Identifierhttp://hdl.handle.net/10722/281970
ISSN

 

DC FieldValueLanguage
dc.contributor.authorQi, Xiaojuan-
dc.contributor.authorChen, Qifeng-
dc.contributor.authorJia, Jiaya-
dc.contributor.authorKoltun, Vladlen-
dc.date.accessioned2020-04-09T09:19:16Z-
dc.date.available2020-04-09T09:19:16Z-
dc.date.issued2018-
dc.identifier.citationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2018, p. 8808-8816-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/10722/281970-
dc.description.abstract© 2018 IEEE. We present a semi-parametric approach to photographic image synthesis from semantic layouts. The approach combines the complementary strengths of parametric and nonparametric techniques. The nonparametric component is a memory bank of image segments constructed from a training set of images. Given a novel semantic layout at test time, the memory bank is used to retrieve photographic references that are provided as source material to a deep network. The synthesis is performed by a deep network that draws on the provided photographic material. Experiments on multiple semantic segmentation datasets show that the presented approach yields considerably more realistic images than recent purely parametric techniques.-
dc.languageeng-
dc.relation.ispartofProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition-
dc.titleSemi-Parametric Image Synthesis-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/CVPR.2018.00918-
dc.identifier.scopuseid_2-s2.0-85062870034-
dc.identifier.spage8808-
dc.identifier.epage8816-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats