Realistic Facial Animation by Automatic Individual Head Modeling and Facial Muscle Adjustment

We propose a technique for automatically generating a realistic facial animation with precise individual facial geometry and characteristic facial expressions. Our method is divided into two key methods: the head modeling process automatically generates a whole head model only from facial range scan data, the facial animation setup process automatically generates key shapes which represent individual facial expressions based on physics-based facial muscle simulation with an individual muscle layout estimated from facial expression videos. Facial animations considering individual characteristics can be synthesized using the generated head model and key shapes. Experimental results show that the proposed method can generate facial animations where 84% of subjects can identify themselves. Therefore, we conclude that our head modeling techniques are effective to entertainment system like a Future Cast.