FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding

arXiv:2312.02214v2 Announce Type: replace
Abstract: We propose FlashAvatar, a novel and lightweight 3D animatable avatar representation that could reconstruct a digital avatar from a short monocular video sequence in minutes and render high-fidelity photo-realistic images at 300FPS on a consumer-grade GPU. To achieve this, we maintain a uniform 3D Gaussian field embedded in the surface of a parametric face model and learn extra spatial offset to model non-surface regions and subtle facial details. While full use of geometric priors can …

arxiv avatar cs.cv cs.gr embedding fidelity head type