Conditional Expression Synthesis with Face Parsing Transformation | |
Zhihe Lu1,2,3; Tanhao Hu1; Lingxiao Song1,4; Zhaoxiang Zhang1,2,3; Ran He1,2,3 | |
2018-10-22 | |
会议名称 | ACM Multimedia conference |
会议日期 | 2018.10.22-2018.10.26 |
会议地点 | Seoul, Korea |
摘要 | Facial expression synthesis with various intensities is a challenging synthesis task due to large identity appearance variations and a paucity of efcient means for intensity measurement. This paper advances the expression synthesis domain by the introduction of a Couple-Agent Face Parsing based Generative Adversarial Network (CAFP-GAN) that unites the knowledge of facial semantic regions and controllable expression signals. Specially, we employ a face parsing map as a controllable condition to guide facial texture generation with a special expression, which can provide a semantic representation of every pixel of facial regions. Our method consists of two sub-networks: face parsing prediction network (FPPN) uses controllable labels (expression and intensity) to generate a face parsing map transformation that corresponds to the labels from the input neutral face, and facial expression synthesis network (FESN) makes the pretrained FPPN as a part of it to provide the face parsing map as a guidance for expression synthesis. To enhance the reality of results, couple-agent discriminators are served to distinguish fake-real pairs in both two sub-nets. Moreover, we only need the neutral face and the labels to synthesize the unknown expression with different intensities. Experimental results on three popular facial expression databases show that our method has the compelling ability on continuous expression synthesis. |
关键词 | Face Parsing Expression Synthesis Generative Adversarial Network |
收录类别 | EI |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/23532 |
专题 | 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 4.Boomhope Information and Technology Co., Ltd |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Zhihe Lu,Tanhao Hu,Lingxiao Song,et al. Conditional Expression Synthesis with Face Parsing Transformation[C],2018. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Conditional expressi(3407KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
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