IPGAN: Identity-Preservation Generative Adversarial Network for unsupervised photo-to-caricature translation

doi:10.1016/j.knosys.2022.108223

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 先进控制与自动化团队

	IPGAN: Identity-Preservation Generative Adversarial Network for unsupervised photo-to-caricature translation
	Yan, Lan 1,3; Zheng, Wenbo 3,4; Gou, Chao 2; Wang, Fei-Yue 3
刊名	KNOWLEDGE-BASED SYSTEMS
	2022-04-06
卷号	241 页码:11
关键词	Photo-to-caricature translation Generative adversarial networks Image-to-image translation Style transfer Image warping
ISSN号	0950-7051
DOI	10.1016/j.knosys.2022.108223
通讯作者	Gou, Chao(gouchao@mail.sysu.edu.cn)
英文摘要	Photo-to-caricature translation is an extremely challenging task because there are not only texture differences between caricatures and photos, but also various spatial deformations in caricatures. Most of existing methods tend to introduce difficult obtained additional information such as precise facial landmarks to guide caricature generation. In addition, identity preservation is a crucial characteristic of caricatures, but unfortunately there seems to be few methods to consider it. Motivated by the aforementioned observations, we propose an Identity-Preservation Generative Adversarial Network (IPGAN) for unsupervised photo-to-caricature translation. In particular, considering the importance of identity retention, we propose a novel identity preservation loss to hold the identity information of original photos and improve the quality of generated caricatures. To capture realistic caricature styles, we design a style differentiation loss to help our model produce caricatures with styles that remarkably differ from photos. Moreover, to learn satisfactory deformations without supervision, our model uses a warp controller to acquire exaggerations automatically that enable to customize diverse exaggerations. As an unsupervised translation method, our IPGAN can also be applied to caricature to-photo translation. Experiments on the WebCaricature dataset suggest that our IPGAN achieves state-of-the-art performance and can generate realistic as well as identity preservation caricatures. (C)& nbsp;2022 Elsevier B.V. All rights reserved.
资助项目	National Key R&D Program of China[2018AAA0101502] ; Key Research and Devel-opment Program of Guangzhou, China[202007050002] ; Natural Science Foundation of China[61806198] ; Natural Science Foundation of China[U1811463]
WOS关键词	IMAGE ; FACES
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000788730900008
资助机构	National Key R&D Program of China ; Key Research and Devel-opment Program of Guangzhou, China ; Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/48440]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队
通讯作者	Gou, Chao
作者单位	1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 2.Sun Yat Sen Univ, Sch Intelligent Syst Engn, Guangzhou, Peoples R China 3.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing, Peoples R China 4.Xi An Jiao Tong Univ, Sch Software Engn, Xian, Peoples R China
推荐引用方式 GB/T 7714	Yan, Lan,Zheng, Wenbo,Gou, Chao,et al. IPGAN: Identity-Preservation Generative Adversarial Network for unsupervised photo-to-caricature translation[J]. KNOWLEDGE-BASED SYSTEMS,2022,241:11.
APA	Yan, Lan,Zheng, Wenbo,Gou, Chao,&Wang, Fei-Yue.(2022).IPGAN: Identity-Preservation Generative Adversarial Network for unsupervised photo-to-caricature translation.KNOWLEDGE-BASED SYSTEMS,241,11.
MLA	Yan, Lan,et al."IPGAN: Identity-Preservation Generative Adversarial Network for unsupervised photo-to-caricature translation".KNOWLEDGE-BASED SYSTEMS 241(2022):11.