高斯头像：通过动态高斯实现超高保真度头像

Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians

December 5, 2023

作者: Yuelang Xu, Benwang Chen, Zhe Li, Hongwen Zhang, Lizhen Wang, Zerong Zheng, Yebin Liu

cs.AI

摘要

创建高保真度的3D头像一直是研究的热点，但在轻量级稀疏视图设置下仍然存在巨大挑战。本文提出了高保真度头像建模的高斯头像，由可控的3D高斯模型表示。我们优化中性3D高斯模型和完全学习的基于MLP的变形场，以捕捉复杂表情。这两部分相互促进，因此我们的方法可以在确保表情准确性的同时建模细粒度动态细节。此外，我们设计了一种基于隐式SDF和深度Marching Tetrahedra的几何引导初始化策略，以确保训练过程的稳定性和收敛性。实验证明，我们的方法胜过其他最先进的稀疏视图方法，在2K分辨率下甚至在夸张表情下实现了超高保真度的渲染质量。

English

Creating high-fidelity 3D head avatars has always been a research hotspot, but there remains a great challenge under lightweight sparse view setups. In this paper, we propose Gaussian Head Avatar represented by controllable 3D Gaussians for high-fidelity head avatar modeling. We optimize the neutral 3D Gaussians and a fully learned MLP-based deformation field to capture complex expressions. The two parts benefit each other, thereby our method can model fine-grained dynamic details while ensuring expression accuracy. Furthermore, we devise a well-designed geometry-guided initialization strategy based on implicit SDF and Deep Marching Tetrahedra for the stability and convergence of the training procedure. Experiments show our approach outperforms other state-of-the-art sparse-view methods, achieving ultra high-fidelity rendering quality at 2K resolution even under exaggerated expressions.