2024
EMAGE: Towards Unified Holistic Co-Speech Gesture Generation via Expressive Masked Audio Gesture Modeling
CVPR 2024poster
We propose EMAGE a framework to generate full-body human gestures from audio and masked gestures encompassing facial local body hands and global movements. To achieve this we first introduce BEAT2 (BEAT-SMPLX-FLAME) a new mesh-level holistic co-speech dataset. BEAT2 combines a MoShed SMPL-X body wit…