FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xiang, Jun, Gao, Xuan, Guo, Yudong, Zhang, Juyong
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913290126360576
author Xiang, Jun
Gao, Xuan
Guo, Yudong
Zhang, Juyong
author_facet Xiang, Jun
Gao, Xuan
Guo, Yudong
Zhang, Juyong
contents 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 capture high-frequency facial details and preserve exaggerated expressions, proper initialization can help reduce the number of Gaussians, thus enabling super-fast rendering speed. Extensive experimental results demonstrate that FlashAvatar outperforms existing works regarding visual quality and personalized details and is almost an order of magnitude faster in rendering speed. Project page: https://ustc3dv.github.io/FlashAvatar/
format Preprint
id arxiv_https___arxiv_org_abs_2312_02214
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding
Xiang, Jun
Gao, Xuan
Guo, Yudong
Zhang, Juyong
Computer Vision and Pattern Recognition
Graphics
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 capture high-frequency facial details and preserve exaggerated expressions, proper initialization can help reduce the number of Gaussians, thus enabling super-fast rendering speed. Extensive experimental results demonstrate that FlashAvatar outperforms existing works regarding visual quality and personalized details and is almost an order of magnitude faster in rendering speed. Project page: https://ustc3dv.github.io/FlashAvatar/
title FlashAvatar: High-fidelity Head Avatar with Efficient Gaussian Embedding
topic Computer Vision and Pattern Recognition
Graphics
url https://arxiv.org/abs/2312.02214