3D Gaussian Blendshapes for Head Avatar Animation

arXiv:2404.19398v1 Announce Type: cross
Abstract: We introduce 3D Gaussian blendshapes for modeling photorealistic head avatars. Taking a monocular video as input, we learn a base head model of neutral expression, along with a group of expression blendshapes, each of which corresponds to a basis expression in classical parametric face models. Both the neutral model and expression blendshapes are represented as 3D Gaussians, which contain a few properties to depict the avatar appearance. The avatar model of an arbitrary expression can …

abstract animation arxiv avatar avatars cs.cv cs.gr face head learn modeling parametric photorealistic type video