GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians

arXiv:2312.02134v2 Announce Type: replace
Abstract: We present GaussianAvatar, an efficient approach to creating realistic human avatars with dynamic 3D appearances from a single video. We start by introducing animatable 3D Gaussians to explicitly represent humans in various poses and clothing styles. Such an explicit and animatable representation can fuse 3D appearances more efficiently and consistently from 2D observations. Our representation is further augmented with dynamic properties to support pose-dependent appearance modeling, where a dynamic appearance network along with an optimizable …

abstract arxiv avatar avatars clothing cs.cv dynamic human humans modeling type via video