Image style disentangling for instance-level facial attribute transfer

doi:10.1016/j.cviu.2021.103205

	Image style disentangling for instance-level facial attribute transfer
	Guo, Xuyang 1,2; Kan, Meina 1; He, Zhenliang 1,2; Song, Xingguang 3; Shan, Shiguang 1
	2021-06-01
发表期刊	COMPUTER VISION AND IMAGE UNDERSTANDING
ISSN	1077-3142
卷号	207 页码:10
摘要	Instance-level facial attribute transfer aims at transferring an attribute including its style from a source face to a target one. Existing studies have limitations on fidelity or correctness. To address this problem, we propose a weakly supervised style disentangling method embedded in Generative Adversarial Network (GAN) for accurate instance-level attribute transfer, using only binary attribute annotations. In our method, the whole attributes transfer process is designed as two steps for easier transfer, which first removes the original attribute or transfers it to a neutral state and then adds the attributes style disentangled from a source face. Moreover, a style disentangling module is proposed to extract the attribute style of an image used in the adding step. Our method aims for accurate attribute style transfer. However, it is also capable of semantic attribute editing as a special case, which is not achievable with existing instance-level attribute transfer methods. Comprehensive experiments on CelebA Dataset show that our method can transfer the style more precisely than existing methods, with an improvement of 39% in user study, 16.5% in accuracy, and about 3.3 in FID.
关键词	Instance-level facial attribute transfer Image to image translation Generative adversarial network Weakly supervised style learning
DOI	10.1016/j.cviu.2021.103205
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2017YFA0700800] ; National Key R&D Program of China[Y808401] ; Natural Science Foundation of China[61772496]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000648965900004
出版者	ACADEMIC PRESS INC ELSEVIER SCIENCE
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/17777
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Kan, Meina
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100049, Peoples R China 3.Huawei Technol Co Ltd, Shenzhen 518129, Peoples R China
推荐引用方式 GB/T 7714	Guo, Xuyang,Kan, Meina,He, Zhenliang,et al. Image style disentangling for instance-level facial attribute transfer[J]. COMPUTER VISION AND IMAGE UNDERSTANDING,2021,207:10.
APA	Guo, Xuyang,Kan, Meina,He, Zhenliang,Song, Xingguang,&Shan, Shiguang.(2021).Image style disentangling for instance-level facial attribute transfer.COMPUTER VISION AND IMAGE UNDERSTANDING,207,10.
MLA	Guo, Xuyang,et al."Image style disentangling for instance-level facial attribute transfer".COMPUTER VISION AND IMAGE UNDERSTANDING 207(2021):10.