中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 先进控制与自动化团队
IsGAN: Identity-sensitive generative adversarial network for face photo-sketch synthesis

文献类型：期刊论文

作者Yan, Lan1,2; Zheng, Wenbo1,3; Gou, Chao4; Wang, Fei-Yue1
刊名PATTERN RECOGNITION
出版日期2021-11-01
卷号119页码:13
关键词Face  photo-sketch synthesis Image-to-image translation Generative adversarial  networks Convolutional  neural  network Face  recognition
ISSN号0031-3203
DOI10.1016/j.patcog.2021.108077
通讯作者Gou, Chao(gouchao@mail.sysu.edu.cn)
英文摘要A B S T R A C T Face photo-sketch synthesis aims to generate face sketches from real photos and vice versa. It can be abstracted as a constrained quantization problem. Although many effort s have been dedicated to this problem, it is still a challenging task to synthesize detail-preserving photos or sketches due to the significant differences between face sketch (drawn by people) and photo (taken by cameras) domains. In this paper, we propose a novel Identity-sensitive Generative Adversarial Network (IsGAN) to address it. Our key insight is to formalize face photo-sketch synthesis as a special case of image-to-image translation and propose to embed identity information through adversarial learning. In particular, an adversarial architecture is used to capture the differences between the two domains, and a new network loss, namely, identity recognition loss is introduced to preserve the detailed identifiable information, which is crucial for photo-sketch synthesis. In addition, to enforce structural consistency during generation, a cyclic-synthesized loss is applied between the generated image of one domain and cycled image of another. The experiments on the CUFS and CUFSF datasets suggest that our model achieves state-of-the-art performance in both qualitative and quantitative measures. (c) 2021 Published by Elsevier Ltd.
资助项目National Key R&D Program of China[2018AAA0101502] ; Key Research and Development Program of Guangzhou[2020 07050 0 02] ; Shenzhen Science and Technology Program[RCBS20200714114920272] ; Natural Science Foundation of China[61806198] ; Natural Science Foundation of China[U1811463]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000687401900005
出版者ELSEVIER SCI LTD
资助机构National Key R&D Program of China ; Key Research and Development Program of Guangzhou ; Shenzhen Science and Technology Program ; Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/45917]  
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.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China
3.Xi An Jiao Tong Univ, Sch Software Engn, Xian, Peoples R China
4.Sun Yat Sen Univ, Sch Intelligent Syst Engn, Guangzhou, Peoples R China
推荐引用方式
GB/T 7714		 Yan, Lan,Zheng, Wenbo,Gou, Chao,et al. IsGAN: Identity-sensitive generative adversarial network for face photo-sketch synthesis[J]. PATTERN RECOGNITION,2021,119:13.
APA Yan, Lan,Zheng, Wenbo,Gou, Chao,&Wang, Fei-Yue.(2021).IsGAN: Identity-sensitive generative adversarial network for face photo-sketch synthesis.PATTERN RECOGNITION,119,13.
MLA Yan, Lan,et al."IsGAN: Identity-sensitive generative adversarial network for face photo-sketch synthesis".PATTERN RECOGNITION 119(2021):13.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。