EmoTaG: Emotion-Aware Talking Head Synthesis on Gaussian Splatting with Few-Shot Personalization

TL;DR

EmoTaG is a novel emotion-aware 3D talking head synthesis framework that improves motion stability and expressiveness by reformulating motion prediction in a structured parameter space and introducing a Gated Residual Motion Network.

Contribution

The paper introduces EmoTaG, a new few-shot emotion-aware talking head synthesis method using structured motion modeling and a specialized neural network for emotional prosody.

Findings

Achieves state-of-the-art results in emotional expressiveness and lip sync.

Improves motion stability and visual realism in 3D talking head synthesis.

Effectively captures emotional prosody from audio cues.

Abstract

Audio-driven 3D talking head synthesis has advanced rapidly with Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS). By leveraging rich pre-trained priors, few-shot methods enable instant personalization from just a few seconds of video. However, under expressive facial motion, existing few-shot approaches often suffer from geometric instability and audio-emotion mismatch, highlighting the need for more effective emotion-aware motion modeling. In this work, we present EmoTaG, a few-shot emotion-aware 3D talking head synthesis framework built on the Pretrain-and-Adapt paradigm. Our key insight is to reformulate motion prediction in a structured FLAME parameter space rather than directly deforming 3D Gaussians, thereby introducing explicit geometric priors that improve motion stability. Building upon this, we propose a Gated Residual Motion Network (GRMN), which captures emotional prosody from audio while supplementing head pose and upper-face cues absent from audio, enabling expressive and coherent motion generation. Extensive experiments demonstrate that EmoTaG achieves state-of-the-art performance in emotional expressiveness, lip synchronization, visual realism, and motion stability.