D^3-Talker: Dual-Branch Decoupled Deformation Fields for Few-Shot 3D Talking Head Synthesis

TL;DR

D^3-Talker introduces a dual-branch framework for few-shot 3D talking head synthesis, effectively decoupling general and personalized deformations to improve lip synchronization and image quality with limited data.

Contribution

It proposes a novel dual-branch deformation model with a similarity contrastive loss for better decoupling and a Coarse-to-Fine module for enhanced image quality in few-shot 3D talking head synthesis.

Findings

Outperforms state-of-the-art in rendering quality

Achieves accurate audio-lip synchronization

Works effectively with limited training data

Abstract

A key challenge in 3D talking head synthesis lies in the reliance on a long-duration talking head video to train a new model for each target identity from scratch. Recent methods have attempted to address this issue by extracting general features from audio through pre-training models. However, since audio contains information irrelevant to lip motion, existing approaches typically struggle to map the given audio to realistic lip behaviors in the target face when trained on only a few frames, causing poor lip synchronization and talking head image quality. This paper proposes D^3-Talker, a novel approach that constructs a static 3D Gaussian attribute field and employs audio and Facial Motion signals to independently control two distinct Gaussian attribute deformation fields, effectively decoupling the predictions of general and personalized deformations. We design a novel similarity contrastive loss function during pre-training to achieve more thorough decoupling. Furthermore, we integrate a Coarse-to-Fine module to refine the rendered images, alleviating blurriness caused by head movements and enhancing overall image quality. Extensive experiments demonstrate that D^3-Talker outperforms state-of-the-art methods in both high-fidelity rendering and accurate audio-lip synchronization with limited training data. Our code will be provided upon acceptance.