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.

翻译：创建高保真度的三维头部头像一直是研究热点，但在使用轻量级稀疏视角设置时仍面临巨大挑战。本文提出由可控三维高斯函数表示的高斯头部头像，用于实现高保真头部头像建模。我们优化中性三维高斯函数和基于完全学习型MLP的形变场，以捕捉复杂的表情变化。这两部分相互促进，使本方法能够在确保表情精度的同时建模精细的动态细节。此外，我们基于隐式SDF和深度行进四面体设计了精心构思的几何引导初始化策略，确保训练过程的稳定性和收敛性。实验表明，本方法优于其他最先进的稀疏视角方法，即使在夸张表情下也能在2K分辨率下实现超高保真渲染质量。