Joint Co-Speech Gesture and Expressive Talking Face Generation using Diffusion with Adapters
This addresses the challenge of integrated human motion generation for applications like virtual avatars, though it is incremental as it builds on existing diffusion and adapter methods.
The paper tackles the problem of generating both co-speech gestures and expressive talking faces jointly, which are typically handled separately, and achieves state-of-the-art performance while reducing parameter count.
Recent advances in co-speech gesture and talking head generation have been impressive, yet most methods focus on only one of the two tasks. Those that attempt to generate both often rely on separate models or network modules, increasing training complexity and ignoring the inherent relationship between face and body movements. To address the challenges, in this paper, we propose a novel model architecture that jointly generates face and body motions within a single network. This approach leverages shared weights between modalities, facilitated by adapters that enable adaptation to a common latent space. Our experiments demonstrate that the proposed framework not only maintains state-of-the-art co-speech gesture and talking head generation performance but also significantly reduces the number of parameters required.