A single transformer diffusion model with cross-modal adapters jointly generates co-speech gestures and expressive talking faces from audio, achieving competitive state-of-the-art metrics with 27.7M parameters.
Diffsheg: A diffusion-based approach for real-time speech-driven holistic 3d expression and ges- ture generation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
Joint Co-Speech Gesture and Expressive Talking Face Generation using Diffusion with Adapters
A single transformer diffusion model with cross-modal adapters jointly generates co-speech gestures and expressive talking faces from audio, achieving competitive state-of-the-art metrics with 27.7M parameters.