4 datasets found

The VOCASET dataset contains 480 paired audio and 3D facial motion sequences captured from 12 subjects.

BIWI dataset has total of 15,678 frames from 24 videos with 20 different subjects captured in the controlled indoor environment.

Speech-driven 3D facial animation is important for many multimedia applications. Recent work has shown promise in using either Diffusion models or Transformer architectures for...

FaceDiffuser is a non-deterministic deep learning model to generate speech-driven facial animations that is trained with both 3D vertex and blendshape based datasets.