File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Self-Enhanced Convolutional Network for Facial Video Hallucination

TitleSelf-Enhanced Convolutional Network for Facial Video Hallucination
Authors
KeywordsSpatial resolution
Face
Image reconstruction
Machine learning
Image restoration
Issue Date2019
PublisherInstitute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=83
Citation
IEEE Transactions on Image Processing, 2019, v. 29, p. 3078-3090 How to Cite?
AbstractAs a domain-specific super-resolution problem, facial image hallucination has enjoyed a series of breakthroughs thanks to the advances of deep convolutional neural networks. However, the direct migration of existing methods to video is still difficult to achieve good performance due to its lack of alignment and consistency modelling in temporal domain. Taking advantage of high inter-frame dependency in videos, we propose a self-enhanced convolutional network for facial video hallucination. It is implemented by making full usage of preceding super-resolved frames and a temporal window of adjacent low-resolution frames. Specifically, the algorithm first obtains the initial high-resolution inference of each frame by taking into consideration a sequence of consecutive low-resolution inputs through temporal consistency modelling. It further recurrently exploits the reconstructed results and intermediate features of a sequence of preceding frames to improve the initial super-resolution of the current frame by modelling the coherence of structural facial features across frames. Quantitative and qualitative evaluations demonstrate the superiority of the proposed algorithm against state-of-the-art methods. Moreover, our algorithm also achieves excellent performance in the task of general video super-resolution in a single-shot setting.
Persistent Identifierhttp://hdl.handle.net/10722/284237
ISSN
2019 Impact Factor: 9.34
2015 SCImago Journal Rankings: 2.727

 

DC FieldValueLanguage
dc.contributor.authorFANG, C-
dc.contributor.authorLI, G-
dc.contributor.authorHAN, X-
dc.contributor.authorYu, Y-
dc.date.accessioned2020-07-20T05:57:08Z-
dc.date.available2020-07-20T05:57:08Z-
dc.date.issued2019-
dc.identifier.citationIEEE Transactions on Image Processing, 2019, v. 29, p. 3078-3090-
dc.identifier.issn1057-7149-
dc.identifier.urihttp://hdl.handle.net/10722/284237-
dc.description.abstractAs a domain-specific super-resolution problem, facial image hallucination has enjoyed a series of breakthroughs thanks to the advances of deep convolutional neural networks. However, the direct migration of existing methods to video is still difficult to achieve good performance due to its lack of alignment and consistency modelling in temporal domain. Taking advantage of high inter-frame dependency in videos, we propose a self-enhanced convolutional network for facial video hallucination. It is implemented by making full usage of preceding super-resolved frames and a temporal window of adjacent low-resolution frames. Specifically, the algorithm first obtains the initial high-resolution inference of each frame by taking into consideration a sequence of consecutive low-resolution inputs through temporal consistency modelling. It further recurrently exploits the reconstructed results and intermediate features of a sequence of preceding frames to improve the initial super-resolution of the current frame by modelling the coherence of structural facial features across frames. Quantitative and qualitative evaluations demonstrate the superiority of the proposed algorithm against state-of-the-art methods. Moreover, our algorithm also achieves excellent performance in the task of general video super-resolution in a single-shot setting.-
dc.languageeng-
dc.publisherInstitute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=83-
dc.relation.ispartofIEEE Transactions on Image Processing-
dc.rightsIEEE Transactions on Image Processing. Copyright © Institute of Electrical and Electronics Engineers.-
dc.rights©20xx IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.-
dc.subjectSpatial resolution-
dc.subjectFace-
dc.subjectImage reconstruction-
dc.subjectMachine learning-
dc.subjectImage restoration-
dc.titleSelf-Enhanced Convolutional Network for Facial Video Hallucination-
dc.typeArticle-
dc.identifier.emailYu, Y: yzyu@cs.hku.hk-
dc.identifier.authorityYu, Y=rp01415-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TIP.2019.2955640-
dc.identifier.scopuseid_2-s2.0-85079575525-
dc.identifier.hkuros310935-
dc.identifier.volume29-
dc.identifier.spage3078-
dc.identifier.epage3090-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats