Neural Voice Puppetry: Audio driven Facial Reenactment

Paper: Project: We present Neural Voice Puppetry, a novel approach for audiodriven facial video synthesis. Given an audio sequence of a source person or digital assistant, we generate a photorealistic output video of a target person that is in sync with the audio of the source input. This audiodriven facial reenactment is driven by a deep neural network that employs a latent 3D face model space. Through the