Multistage adversarial losses for pose-based human image synthesis | |
Si, Chenyang1,3; Wang, Wei1,3; Wang, Liang1,2,3; Tan, Tieniu1,2,3 | |
2018 | |
会议日期 | 2018 |
会议地点 | Salt Lake City, Utah |
英文摘要 | Human image synthesis has extensive practical applications e.g. person re-identification and data augmentation for human pose estimation. However, it is much more challenging than rigid object synthesis, e.g. cars and chairs, due to the variability of human posture. In this paper, we propose a pose-based human image synthesis method which can keep the human posture unchanged in novel viewpoints. Furthermore, we adopt multistage adversarial losses separately for the foreground and background generation, which fully exploits the multi-modal characteristics of generative loss to generate more realistic looking images. We perform extensive experiments on the Human3.6M dataset and verify the effectiveness of each stage of our method. The generated human images not only keep the same pose as the input image, but also have clear detailed foreground and background. The quantitative comparison results illustrate that our approach achieves much better results than several state-of-the-art methods. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/44298] ![]() |
专题 | 自动化研究所_智能感知与计算研究中心 |
通讯作者 | Wang, Wei |
作者单位 | 1.Center for Excellence in Brain Science and Intelligence Technology (CEBSIT), Institute of Automation, Chinese Academy of Sciences (CASIA) 2.University of Chinese Academy of Sciences (UCAS) 3.Center for Research on Intelligent Perception and Computing (CRIPAC), National Laboratory of Pattern Recognition (NLPR) |
推荐引用方式 GB/T 7714 | Si, Chenyang,Wang, Wei,Wang, Liang,et al. Multistage adversarial losses for pose-based human image synthesis[C]. 见:. Salt Lake City, Utah. 2018. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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