Geometry Guided Adversarial Facial Expression Synthesis | |
Lingxiao Song1; Zhihe Lu1,2,3; Ran He1,2,3; Zhenan Sun1,2,3; Tieniu Tan1,2,3 | |
2018-10-22 | |
会议日期 | 2018.10.22-2018.10.26 |
会议地点 | Seoul, Korea |
关键词 | Facial Expression Synthesis Generative Adversarial Networks Unpaired Image-to-image Transformation |
英文摘要 | Facial expression synthesis has drawn much attention in the feld of computer graphics and pattern recognition. It has been widely used in face animation and recognition. However, it is still challenging due to the high-level semantic presence of large and non-linear face geometry variations. This paper proposes a Geometry-Guided Generative Adversarial Network (G2-GAN) for continuously-adjusting and identity-preserving facial expression synthesis. We employ facial geometry (fducial points) as a controllable condition to guide facial texture synthesis with specifc expression. A pair of generative adversarial subnetworks is jointly trained towards opposite tasks: expression removal and expression synthesis. The paired networks form a mapping cycle between neutral expression and arbitrary expressions, with which the proposed approach can be conducted among unpaired data. The proposed paired networks also facilitate other applications such as face transfer, expression interpolation and expression-invariant face recognition. Experimental results on several facial expression databases show that our method can generate compelling perceptual results on different expression editing tasks. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/23533] |
专题 | 自动化研究所_智能感知与计算研究中心 |
通讯作者 | Ran He |
作者单位 | 1.Center for Research on Intelligent Perception and Computing, CASIA 2.Center for Excellence in Brain Science and Intelligence Technology, CAS 3.University of Chinese Academy of Sciences, Beijing, 100049, China |
推荐引用方式 GB/T 7714 | Lingxiao Song,Zhihe Lu,Ran He,et al. Geometry Guided Adversarial Facial Expression Synthesis[C]. 见:. Seoul, Korea. 2018.10.22-2018.10.26. |
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