GaussianTalker: Speaker-specific Talking Head Synthesis via 3D Gaussian Splatting

TL;DR

GaussianTalker introduces a novel 3D Gaussian Splatting-based approach for audio-driven talking head synthesis, achieving realistic, synchronized lip movements and high-speed rendering suitable for real-time applications.

Contribution

The paper presents GaussianTalker, a new method that explicitly controls facial motion using 3D Gaussian representations, improving synchronization and visual quality over prior NeRF-based techniques.

Findings

Outperforms state-of-the-art in lip synchronization and visual quality

Achieves 130 FPS rendering speed on NVIDIA RTX4090

Provides stable, realistic talking head videos

Abstract

Recent works on audio-driven talking head synthesis using Neural Radiance Fields (NeRF) have achieved impressive results. However, due to inadequate pose and expression control caused by NeRF implicit representation, these methods still have some limitations, such as unsynchronized or unnatural lip movements, and visual jitter and artifacts. In this paper, we propose GaussianTalker, a novel method for audio-driven talking head synthesis based on 3D Gaussian Splatting. With the explicit representation property of 3D Gaussians, intuitive control of the facial motion is achieved by binding Gaussians to 3D facial models. GaussianTalker consists of two modules, Speaker-specific Motion Translator and Dynamic Gaussian Renderer. Speaker-specific Motion Translator achieves accurate lip movements specific to the target speaker through universalized audio feature extraction and customized lip motion generation. Dynamic Gaussian Renderer introduces Speaker-specific BlendShapes to enhance facial detail representation via a latent pose, delivering stable and realistic rendered videos. Extensive experimental results suggest that GaussianTalker outperforms existing state-of-the-art methods in talking head synthesis, delivering precise lip synchronization and exceptional visual quality. Our method achieves rendering speeds of 130 FPS on NVIDIA RTX4090 GPU, significantly exceeding the threshold for real-time rendering performance, and can potentially be deployed on other hardware platforms.