MakeItTalk: Speaker-Aware Talking-Head Animation
This addresses the problem of creating realistic and speaker-specific talking-head videos for applications in animation and media, representing a novel method rather than an incremental improvement.
The paper tackles generating expressive talking-head animations from a single image and audio by disentangling audio content and speaker information, resulting in significantly higher quality outputs compared to prior state-of-the-art methods.
We present a method that generates expressive talking heads from a single facial image with audio as the only input. In contrast to previous approaches that attempt to learn direct mappings from audio to raw pixels or points for creating talking faces, our method first disentangles the content and speaker information in the input audio signal. The audio content robustly controls the motion of lips and nearby facial regions, while the speaker information determines the specifics of facial expressions and the rest of the talking head dynamics. Another key component of our method is the prediction of facial landmarks reflecting speaker-aware dynamics. Based on this intermediate representation, our method is able to synthesize photorealistic videos of entire talking heads with full range of motion and also animate artistic paintings, sketches, 2D cartoon characters, Japanese mangas, stylized caricatures in a single unified framework. We present extensive quantitative and qualitative evaluation of our method, in addition to user studies, demonstrating generated talking heads of significantly higher quality compared to prior state-of-the-art.