File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TIP.2019.2955640
- Scopus: eid_2-s2.0-85079575525
- WOS: WOS:000510750900015
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Self-Enhanced Convolutional Network for Facial Video Hallucination
Title | Self-Enhanced Convolutional Network for Facial Video Hallucination |
---|---|
Authors | |
Keywords | Spatial resolution Face Image reconstruction Machine learning Image restoration |
Issue Date | 2019 |
Publisher | Institute 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? |
Abstract | As 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 Identifier | http://hdl.handle.net/10722/284237 |
ISSN | 2023 Impact Factor: 10.8 2023 SCImago Journal Rankings: 3.556 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | FANG, C | - |
dc.contributor.author | LI, G | - |
dc.contributor.author | HAN, X | - |
dc.contributor.author | Yu, Y | - |
dc.date.accessioned | 2020-07-20T05:57:08Z | - |
dc.date.available | 2020-07-20T05:57:08Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | IEEE Transactions on Image Processing, 2019, v. 29, p. 3078-3090 | - |
dc.identifier.issn | 1057-7149 | - |
dc.identifier.uri | http://hdl.handle.net/10722/284237 | - |
dc.description.abstract | As 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.language | eng | - |
dc.publisher | Institute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=83 | - |
dc.relation.ispartof | IEEE Transactions on Image Processing | - |
dc.rights | IEEE 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.subject | Spatial resolution | - |
dc.subject | Face | - |
dc.subject | Image reconstruction | - |
dc.subject | Machine learning | - |
dc.subject | Image restoration | - |
dc.title | Self-Enhanced Convolutional Network for Facial Video Hallucination | - |
dc.type | Article | - |
dc.identifier.email | Yu, Y: yzyu@cs.hku.hk | - |
dc.identifier.authority | Yu, Y=rp01415 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/TIP.2019.2955640 | - |
dc.identifier.scopus | eid_2-s2.0-85079575525 | - |
dc.identifier.hkuros | 310935 | - |
dc.identifier.volume | 29 | - |
dc.identifier.spage | 3078 | - |
dc.identifier.epage | 3090 | - |
dc.identifier.isi | WOS:000510750900015 | - |
dc.publisher.place | United States | - |
dc.identifier.issnl | 1057-7149 | - |