EAvatar: Expression-Aware Head Avatar Reconstruction with Generative Geometry Priors

TL;DR

EAvatar is a novel head avatar reconstruction method that uses generative geometry priors and sparse expression control to accurately model facial expressions and textures in real-time, advancing AR/VR and multimedia applications.

Contribution

It introduces a new expression-aware 3D Gaussian Splatting framework utilizing generative priors and sparse control for detailed, stable head avatar reconstruction.

Findings

More accurate head reconstructions with better expression control.

Improved detail fidelity and shape accuracy.

Enhanced convergence stability during training.

Abstract

High-fidelity head avatar reconstruction plays a crucial role in AR/VR, gaming, and multimedia content creation. Recent advances in 3D Gaussian Splatting (3DGS) have demonstrated effectiveness in modeling complex geometry with real-time rendering capability and are now widely used in high-fidelity head avatar reconstruction tasks. However, existing 3DGS-based methods still face significant challenges in capturing fine-grained facial expressions and preserving local texture continuity, especially in highly deformable regions. To mitigate these limitations, we propose a novel 3DGS-based framework termed EAvatar for head reconstruction that is both expression-aware and deformation-aware. Our method introduces a sparse expression control mechanism, where a small number of key Gaussians are used to influence the deformation of their neighboring Gaussians, enabling accurate modeling of local deformations and fine-scale texture transitions. Furthermore, we leverage high-quality 3D priors from pretrained generative models to provide a more reliable facial geometry, offering structural guidance that improves convergence stability and shape accuracy during training. Experimental results demonstrate that our method produces more accurate and visually coherent head reconstructions with improved expression controllability and detail fidelity.