Knowledge Commons of Institute of Automation,CAS
IsGAN: Identity-sensitive generative adversarial network for face photo-sketch synthesis | |
Yan, Lan1,2![]() ![]() ![]() | |
发表期刊 | PATTERN RECOGNITION
![]() |
ISSN | 0031-3203 |
2021-11-01 | |
卷号 | 119页码:13 |
摘要 | 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. |
关键词 | Face photo-sketch synthesis Image-to-image translation Generative adversarial networks Convolutional neural network Face recognition |
DOI | 10.1016/j.patcog.2021.108077 |
收录类别 | SCI |
语种 | 英语 |
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] |
项目资助者 | National Key R&D Program of China ; Key Research and Development Program of Guangzhou ; Shenzhen Science and Technology Program ; Natural Science Foundation of China |
WOS研究方向 | Computer Science ; Engineering |
WOS类目 | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000687401900005 |
出版者 | ELSEVIER SCI LTD |
七大方向——子方向分类 | 生物特征识别 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/45918 |
专题 | 多模态人工智能系统全国重点实验室_平行智能技术与系统团队 |
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 |
第一作者单位 | 中国科学院自动化研究所 |
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. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
IsGAN: Identity-sens(4465KB) | 期刊论文 | 出版稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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。
修改评论