CAJ | 학술논문

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.
위료중용시빈내용중적표정신식, 제출일충어의표정구조여어의표정삼수우화방법. 수선종대유조성적희소특정점중정의출인검표정적어의신식; 연후재어의표정공간중우화구해출최우표정삼수, 이제고인검동화적진실감. 해방법기불수요표정상궤삼수, 야불수요예선건립표연자적3D인검모형급기표정기, 인차제료가용우망락시빈적표정중용,야가용우개발실시재선적망락사교등응용.실험결과표명,대우두부파동적부앙각화측각재[?15?, 15?]범위내적원시시빈, 문중방법능구실시합성은정、핍진적표정동화.
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 from15 to 15?.