SIA OpenIR  > 机器人学研究室
Laplacian pyramid adversarial network for face completion
Wang Q(王强)1,2; Fan HJ(范慧杰)1; Sun G(孙干)1,2; Cong Y(丛杨)1; Tang YD(唐延东)1
Department机器人学研究室
Source PublicationPattern Recognition
ISSN0031-3203
2019
Volume88Pages:493-505
Indexed BySCI ; EI
EI Accession number20185006247297
WOS IDWOS:000457666900039
Contribution Rank1
Funding OrganizationNational Natural Science Foundation of China
KeywordFace completion Generative adversarial network Laplacian pyramid
AbstractRecently, generative adversarial networks (GANs) have demonstrated high-quality reconstruction in face completion. There is still much room for improvement over the conventional GAN models that do not explicitly address the texture details problem. In this paper, we propose a Laplacian-pyramid-based generative framework for face completion. This framework can produce more realistic results (1) by deriving precise content information of missing face regions in a coarse-to-fine fashion and (2) by propagating the high-frequency details from the surrounding area via a modified residual learning model. Specifically, for the missing regions, we design a Laplacian-pyramid-based convolutional network framework that can predict missing regions under different resolutions; this framework takes advantage of multiscale features shared from low levels and extracted from middle layers for the next finer level. For high-frequency details, we construct a new residual learning network to eliminate color discrepancies between the missing and surrounding regions progressively. Furthermore, a multiloss function is proposed to supervise the generative process. To optimize the model, we train the entire generative model with deep supervision using a joint reconstruction loss, which ensures that the generated image is as realistic as the original. Extensive experiments on benchmark datasets show that the proposed framework exhibits superior performance over state-of-the-art methods in terms of predictive accuracy, both quantitatively and qualitatively.
Language英语
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS Research AreaComputer Science ; Engineering
Funding ProjectNational Natural Science Foundation of China[U1613214] ; 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[U1613214]
Citation statistics
Cited Times:1[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/23870
Collection机器人学研究室
Corresponding AuthorFan HJ(范慧杰)
Affiliation1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, 110016, China
2.University of Chinese Academy of Sciences, Beijing 100049, China
Recommended Citation
GB/T 7714
Wang Q,Fan HJ,Sun G,et al. Laplacian pyramid adversarial network for face completion[J]. Pattern Recognition,2019,88:493-505.
APA Wang Q,Fan HJ,Sun G,Cong Y,&Tang YD.(2019).Laplacian pyramid adversarial network for face completion.Pattern Recognition,88,493-505.
MLA Wang Q,et al."Laplacian pyramid adversarial network for face completion".Pattern Recognition 88(2019):493-505.
Files in This Item: Download All
File Name/Size DocType Version Access License
Laplacian Pyramid Ad(9181KB)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
[Sun G(孙干)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang Q(王强)]'s Articles
[Fan HJ(范慧杰)]'s Articles
[Sun G(孙干)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang Q(王强)]'s Articles
[Fan HJ(范慧杰)]'s Articles
[Sun G(孙干)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Laplacian Pyramid Adversarial Network for Face Completion.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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