中文摘要：

为了重用视频内容中的表情信息,提出一种语义表情构造与语义表情参数优化方法。首先从带有噪声的稀疏特征点中定义出人脸表情的语义信息；然后在语义表情空间中优化求解出最优表情参数,以提高人脸动画的真实感。该方法既不需要标定相机参数,也不需要预先建立表演者的3D人脸模型及其表情基,因此除了可用于网络视频的表情重用,也可用于开发实时在线的网络社交等应用。实验结果表明,对于头部摆动的俯仰角和侧角在[-15°,15°]范围内的原始视频,文中方法能够实时合成稳定、逼真的表情动画。

英文摘要：

This paper proposes a novel method about semantic expression definition and optimization. The pro-posed method solves the real-time video-driven facial retargeting problem. First, it defines a set of semantic val-ues, which represents the expression, from sparse 2D feature points with noise. Then, an extended optimization solved in semantic space is employed to improve the quality of expression retargeting. The method neither needs to calibrate camera, nor requires user-specific training to construct the special 3D model and blendshape. So, the proposed algorithm can be applied widely for retargeting expression of network video, real-time social networks, and so on. The experiments demonstrates that the proposed method can achieve accurate and stable facial anima-tion results with the pitch and yaw ranged from-15＆#176; to 15＆#176;.