Gaussian Eigen Models for Human Heads

Understand

Current personalized neural head avatars face a trade-off: lightweight models lack detail and realism, while high-quality, animatable avatars require significant computational resources, making them unsuitable for commodity devices.

• To address this gap, we introduce Gaussian Eigen Models (GEM), which provide high-quality, lightweight, and easily controllable head avatars.
• GEM utilizes 3D Gaussian primitives for representing the appearance combined with Gaussian splatting for rendering.
• Building on the success of mesh-based 3D morphable face models (3DMM), we define GEM as an ensemble of linear eigenbases for representing the head appearance of a specific subject.