Follow
DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation. (arXiv:2401.04747v1 [cs.SD]) http://arxiv.org/abs/2401.04747
DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation. (arXiv:2401.04747v1 [cs.SD]) http://arxiv.org/abs/2401.04747