Live Speech Portraits: Real-Time Photorealistic Talking-Head Animation
This addresses the problem of creating realistic, personalized video avatars in real-time for applications like virtual communication or entertainment, representing a novel method for a known bottleneck.
The paper tackles real-time photorealistic talking-head animation driven by audio signals, achieving over 30 fps and generating high-fidelity personalized facial details like wrinkles and teeth, with extensive evaluations showing superiority over state-of-the-art techniques.
To the best of our knowledge, we first present a live system that generates personalized photorealistic talking-head animation only driven by audio signals at over 30 fps. Our system contains three stages. The first stage is a deep neural network that extracts deep audio features along with a manifold projection to project the features to the target person's speech space. In the second stage, we learn facial dynamics and motions from the projected audio features. The predicted motions include head poses and upper body motions, where the former is generated by an autoregressive probabilistic model which models the head pose distribution of the target person. Upper body motions are deduced from head poses. In the final stage, we generate conditional feature maps from previous predictions and send them with a candidate image set to an image-to-image translation network to synthesize photorealistic renderings. Our method generalizes well to wild audio and successfully synthesizes high-fidelity personalized facial details, e.g., wrinkles, teeth. Our method also allows explicit control of head poses. Extensive qualitative and quantitative evaluations, along with user studies, demonstrate the superiority of our method over state-of-the-art techniques.