Driven facial animation

30 Jul We present a machine learning technique for driving 3D facial animation by audio input in real time and with low latency. Our deep neural.

Fig. 1. Our deep neural network for inferring facial animation from speech. The network takes approximately half a second of audio as input, and outputs the. Yang Yang, Nanning Zheng, Yuehu Liu, Shaoyi Du, Yoshifumi Nishio, Example-based performance driven facial shape animation, Proceedings of the