SIA OpenIR  > 机器人学研究室
Deeply Supervised Face Completion With Multi-Context Generative Adversarial Network
Wang Q(王强)1,2,3; Fan HJ(范慧杰)1,2; Zhu LL(朱琳琳)4; Tang YD(唐延东)1,2
Department机器人学研究室
Source PublicationIEEE SIGNAL PROCESSING LETTERS
ISSN1070-9908
2019
Volume26Issue:3Pages:400-404
Indexed BySCI ; EI
EI Accession number20190606476932
WOS IDWOS:000457376100001
Contribution Rank1
Funding OrganizationNational Natural Science Foundation of China ; State Key Laboratory of Robotics Open Project
KeywordFace completion multi-context generative adversarial network
AbstractRecent face completion works have achieved significant improvement using generative adversarial networks (GANs). There are still two important issues in this challenging task: first, semantic understanding; and second, high-frequency details prediction. In this letter, we propose a unified model by introducing multicontext structures within GANs. Our model, named multi-context generative adversarial networks (MCGAN), automatically learns the hierarchical appearances of a corrupted image and predicted the missing regions from different perspectives. In this model, semantic understanding and high-frequency details are both taken into account and modeled with two parallel networks, respectively. While one learns the semantic understanding of the input face image at a high level, the other extracts low-level features for highfrequency details prediction. Our MCGAN takes full advantage of multi-scale features learned from two complementary networks and generates semantically new pixels for the missing region with fine details. Extensive quantitative and qualitative experiments on benchmark datasets show that the proposed model outperforms several state-of-the-art models.
Language英语
WOS SubjectEngineering, Electrical & Electronic
WOS Research AreaEngineering
Funding ProjectState Key Laboratory of Robotics Open Project[2015-212] ; National Natural Science Foundation of China[61503256] ; National Natural Science Foundation of China[61333019] ; National Natural Science Foundation of China[61873259] ; National Natural Science Foundation of China[61873259] ; National Natural Science Foundation of China[61333019] ; National Natural Science Foundation of China[61503256] ; State Key Laboratory of Robotics Open Project[2015-212]
Citation statistics
Cited Times:1[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/24154
Collection机器人学研究室
Corresponding AuthorFan HJ(范慧杰)
Affiliation1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
2.Institute of Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110016, China
3.University of Chinese Academy of Sciences, Beijing 100049, China
4.College of Automation, Shenyang Aerospace University, Shenyang 110136, China
Recommended Citation
GB/T 7714
Wang Q,Fan HJ,Zhu LL,et al. Deeply Supervised Face Completion With Multi-Context Generative Adversarial Network[J]. IEEE SIGNAL PROCESSING LETTERS,2019,26(3):400-404.
APA Wang Q,Fan HJ,Zhu LL,&Tang YD.(2019).Deeply Supervised Face Completion With Multi-Context Generative Adversarial Network.IEEE SIGNAL PROCESSING LETTERS,26(3),400-404.
MLA Wang Q,et al."Deeply Supervised Face Completion With Multi-Context Generative Adversarial Network".IEEE SIGNAL PROCESSING LETTERS 26.3(2019):400-404.
Files in This Item: Download All
File Name/Size DocType Version Access License
Deeply Supervised Fa(1601KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang Q(王强)]'s Articles
[Fan HJ(范慧杰)]'s Articles
[Zhu LL(朱琳琳)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang Q(王强)]'s Articles
[Fan HJ(范慧杰)]'s Articles
[Zhu LL(朱琳琳)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang Q(王强)]'s Articles
[Fan HJ(范慧杰)]'s Articles
[Zhu LL(朱琳琳)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Deeply Supervised Face Completion With Multi-Context Generative Adversarial Network.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.