GGTalker: Talking Head Systhesis with Generalizable Gaussian Priors and Identity-Specific Adaptation

TL;DR

GGTalker is a novel framework for synthesizing high-quality, generalizable 3D talking heads by leveraging Gaussian priors and identity-specific adaptation, addressing limitations of previous methods in large head rotations and out-of-distribution audio.

Contribution

It introduces a two-stage Prior-Adaptation training strategy with Gaussian priors and a color MLP, enabling efficient, high-quality, and personalized talking head synthesis.

Findings

Achieves state-of-the-art rendering quality and 3D consistency

Handles large head rotations and out-of-distribution audio effectively

Improves training efficiency over previous methods

Abstract

Creating high-quality, generalizable speech-driven 3D talking heads remains a persistent challenge. Previous methods achieve satisfactory results for fixed viewpoints and small-scale audio variations, but they struggle with large head rotations and out-of-distribution (OOD) audio. Moreover, they are constrained by the need for time-consuming, identity-specific training. We believe the core issue lies in the lack of sufficient 3D priors, which limits the extrapolation capabilities of synthesized talking heads. To address this, we propose GGTalker, which synthesizes talking heads through a combination of generalizable priors and identity-specific adaptation. We introduce a two-stage Prior-Adaptation training strategy to learn Gaussian head priors and adapt to individual characteristics. We train Audio-Expression and Expression-Visual priors to capture the universal patterns of lip movements and the general distribution of head textures. During the Customized Adaptation, individual speaking styles and texture details are precisely modeled. Additionally, we introduce a color MLP to generate fine-grained, motion-aligned textures and a Body Inpainter to blend rendered results with the background, producing indistinguishable, photorealistic video frames. Comprehensive experiments show that GGTalker achieves state-of-the-art performance in rendering quality, 3D consistency, lip-sync accuracy, and training efficiency.