File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Image inpainting via generative multi-column convolutional neural networks

TitleImage inpainting via generative multi-column convolutional neural networks
Authors
Issue Date2018
Citation
32nd Conference on Neural Information Processing Systems (NIPS 2018), Montreal, Canada, 2-8 December 2018. In Advances in Neural Information Processing Systems, 2018, v. 2018-December, p. 331-340 How to Cite?
Abstract© 2018 Curran Associates Inc..All rights reserved. In this paper, we propose a generative multi-column network for image inpainting. This network synthesizes different image components in a parallel manner within one stage. To better characterize global structures, we design a confidence-driven reconstruction loss while an implicit diversified MRF regularization is adopted to enhance local details. The multi-column network combined with the reconstruction and MRF loss propagates local and global information derived from context to the target inpainting regions. Extensive experiments on challenging street view, face, natural objects and scenes manifest that our method produces visual compelling results even without previously common post-processing.
Persistent Identifierhttp://hdl.handle.net/10722/281954
ISSN
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorWang, Yi-
dc.contributor.authorTao, Xin-
dc.contributor.authorQi, Xiaojuan-
dc.contributor.authorShen, Xiaoyong-
dc.contributor.authorJia, Jiaya-
dc.date.accessioned2020-04-09T09:19:13Z-
dc.date.available2020-04-09T09:19:13Z-
dc.date.issued2018-
dc.identifier.citation32nd Conference on Neural Information Processing Systems (NIPS 2018), Montreal, Canada, 2-8 December 2018. In Advances in Neural Information Processing Systems, 2018, v. 2018-December, p. 331-340-
dc.identifier.issn1049-5258-
dc.identifier.urihttp://hdl.handle.net/10722/281954-
dc.description.abstract© 2018 Curran Associates Inc..All rights reserved. In this paper, we propose a generative multi-column network for image inpainting. This network synthesizes different image components in a parallel manner within one stage. To better characterize global structures, we design a confidence-driven reconstruction loss while an implicit diversified MRF regularization is adopted to enhance local details. The multi-column network combined with the reconstruction and MRF loss propagates local and global information derived from context to the target inpainting regions. Extensive experiments on challenging street view, face, natural objects and scenes manifest that our method produces visual compelling results even without previously common post-processing.-
dc.languageeng-
dc.relation.ispartofAdvances in Neural Information Processing Systems-
dc.titleImage inpainting via generative multi-column convolutional neural networks-
dc.typeConference_Paper-
dc.identifier.scopuseid_2-s2.0-85064819449-
dc.identifier.volume2018-December-
dc.identifier.spage331-
dc.identifier.epage340-
dc.identifier.isiWOS:000461823300031-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats