基于运动轨迹分析的3D唇舌肌肉控制模型

针对可视化语音以及虚拟说话人系统中对唇部和舌部动画的高逼真度要求, 提出了一种基于运动轨迹分析的3D唇舌肌肉控制模型。该方法首先根据解剖学原理, 建立基于网格和纹理的唇部、舌部模型。然后, 根据分析唇部的运动轨迹, 将口轮匝肌分解成两部分来联合控制唇部的运动, 可以获得各种口型。在舌部的运动模拟中, 将它的运动轨迹分解成一些机械运动的组合, 通过使用四种肌肉模型来控制这些运动。最终实现了人脸嘴部说话时的各种口型, 实现了卷舌、舔嘴等动作。实验结果表明, 该方法能逼真地实现出唇部、舌部的运动动画。

Mouth and tongue model controlled by muscles based on motion trail analyzing

The animation of lip-synching in visual voice technology or talking head system is a very important part. This paper presented a new method about controlling the movement of the mouth and tongue's 3-D (three-dimensional) model. Firstly, it built a tongue model according to the anatomy, and a mouth model based on meshes and texture model. Then, through analyzing the lip's motion, it used the method of dividing the orbicularis oris into two parts to imitate the lip's motion trail. In the part of tongue's motion simulation, according to its trail, divided it into some kinds of mechanical motions' combination and used four kinds of muscles to control these motions. Finally, it realized mouth's shape when people talking, and tongue's movements like rotating up, moving side-to-side and so on. The experiments show that the method can vividly simulate the mouth and the tongue's motion.