HeadGaS: Real-Time Animatable Head Avatars via 3D Gaussian Splatting
This work addresses the need for real-time animatable head avatars in applications like virtual reality, though it is incremental as it builds on existing 3D Gaussian Splatting methods.
The paper tackled the problem of real-time 3D head animation by proposing HeadGaS, a model that uses 3D Gaussian Splats with learnable latent features, achieving state-of-the-art results with up to 2dB improvement and over 10x faster rendering speed.
3D head animation has seen major quality and runtime improvements over the last few years, particularly empowered by the advances in differentiable rendering and neural radiance fields. Real-time rendering is a highly desirable goal for real-world applications. We propose HeadGaS, a model that uses 3D Gaussian Splats (3DGS) for 3D head reconstruction and animation. In this paper we introduce a hybrid model that extends the explicit 3DGS representation with a base of learnable latent features, which can be linearly blended with low-dimensional parameters from parametric head models to obtain expression-dependent color and opacity values. We demonstrate that HeadGaS delivers state-of-the-art results in real-time inference frame rates, surpassing baselines by up to 2dB, while accelerating rendering speed by over x10.