Data-Driven Synthesis of Cartoon Faces Using Different Styles

doi:10.1109/TIP.2016.2628581

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 多媒体计算与图形学团队

	Data-Driven Synthesis of Cartoon Faces Using Different Styles
	Zhang, Yong1,2,3 ; Dong, Weiming1,2 ; Ma, Chongyang 4; Mei, Xing1,2 ; Li, Ke 5; Huang, Feiyue ; Hu, Bao-Gang1,2 ; Deussen, Oliver 6,7
刊名	IEEE TRANSACTIONS ON IMAGE PROCESSING
	2017
卷号	26 期号:1 页码:464-478
关键词	Cartoon Face Face Stylization Data-driven Synthesis Component-based Modeling
DOI	10.1109/TIP.2016.2628581
文献子类	Article
英文摘要	This paper presents a data-driven approach for automatically generating cartoon faces in different styles from a given portrait image. Our stylization pipeline consists of two steps: an offline analysis step to learn about how to select and compose facial components from the databases; a runtime synthesis step to generate the cartoon face by assembling parts from a database of stylized facial components. We propose an optimization framework that, for a given artistic style, simultaneously considers the desired image-cartoon relationships of the facial components and a proper adjustment of the image composition. We measure the similarity between facial components of the input image and our cartoon database via image feature matching, and introduce a probabilistic framework for modeling the relationships between cartoon facial components. We incorporate prior knowledge about image-cartoon relationships and the optimal composition of facial components extracted from a set of cartoon faces to maintain a natural, consistent, and attractive look of the results. We demonstrate generality and robustness of our approach by applying it to a variety of portrait images and compare our output with stylized results created by artists via a comprehensive user study.
WOS关键词	SKETCH SYNTHESIS ; REPRESENTATION
WOS研究方向	Computer Science ; Engineering
语种	英语
WOS记录号	WOS:000397221700010
资助机构	National Natural Science Foundation of China(61672520 ; Beijing Natural Science Foundation(4162056) ; National Foreign Thousand Talents Plan(WQ201344000169) ; Leading Talents of Guangdong Program(00201509) ; CASIA Tencent Youtu Joint Research Project ; 61573348 ; 61271430 ; 61372184)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/12378]
专题	自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
通讯作者	Dong, Weiming
作者单位	1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Inst Automat, Lab Comp Sci Automat & Appl Math, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 4.Univ Southern Calif, Los Angeles, CA 90007 USA 5.Youtu Lab, Shanghai 200233, Peoples R China 6.Univ Konstanz, D-78457 Constance, Germany 7.Shenzhen Inst Adv Technol, Shenzhen 518172, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Yong,Dong, Weiming,Ma, Chongyang,et al. Data-Driven Synthesis of Cartoon Faces Using Different Styles[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2017,26(1):464-478.
APA	Zhang, Yong.,Dong, Weiming.,Ma, Chongyang.,Mei, Xing.,Li, Ke.,...&Deussen, Oliver.(2017).Data-Driven Synthesis of Cartoon Faces Using Different Styles.IEEE TRANSACTIONS ON IMAGE PROCESSING,26(1),464-478.
MLA	Zhang, Yong,et al."Data-Driven Synthesis of Cartoon Faces Using Different Styles".IEEE TRANSACTIONS ON IMAGE PROCESSING 26.1(2017):464-478.