Pose-Guided Photorealistic Face Rotation | |
Yibo Hu1,2; Xiang Wu1; Bing Yu3; Ran He(赫然)1,2; Zhenan Sun1,2 | |
2018 | |
会议名称 | IEEE Computer Vision and Pattern Recognition |
会议日期 | 2018 |
会议地点 | Salt Lake City, USA |
摘要 | Face rotation provides an effective and cheap way for data augmentation and representation learning of face recognition. It is a challenging generative learning problem due to the large pose discrepancy between two face images. This work focuses on flexible face rotation of arbitrary head poses, including extreme profile views. We propose a novel Couple-Agent Pose-Guided Generative Adversarial Network (CAPG-GAN) to generate both neutral and profile head pose face images. The head pose information is encoded by facial landmark heatmaps. It not only forms a mask image to guide the generator in learning process but also provides a flexible controllable condition during inference. A couple-agent discriminator is introduced to reinforce on the realism of synthetic arbitrary view faces. Besides the generator and conditional adversarial loss, CAPG-GAN further employs identity preserving loss and total variation regularization to preserve identity information and refine local textures respectively. Quantitative and qualitative experimental results on the Multi-PIE and LFW databases consistently show the superiority of our face rotation method over the state-of-the-art. |
关键词 | Face Rotation Couple-agent Pose-guided Generative Adversarial Network Generative Learning |
收录类别 | EI |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/21089 |
专题 | 智能感知与计算研究中心 |
作者单位 | 1.Center for Research on Intelligent Perception and Computing, National Laboratory of Pattern Recognition, Center for Excellence in Brain Science and Intelligence Technology, Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences 3.Noah’s Ark Laboratory, Huawei Technologies Co., Ltd. |
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 | Yibo Hu,Xiang Wu,Bing Yu,et al. Pose-Guided Photorealistic Face Rotation[C],2018. |
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 | ||
1097.pdf(2313KB) | 会议论文 | 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