Mimic: Speaking Style Disentanglement for Speech-Driven 3D Facial Animation

TL;DR

This paper introduces Mimic, a novel framework for disentangling speaking style and content in speech-driven 3D facial animation, leading to more realistic and diverse facial animations by modeling subject-specific speaking styles.

Contribution

It presents the first method to explicitly disentangle speaking style from content in facial motion, enabling arbitrary style encoding and improved animation realism.

Findings

Outperforms state-of-the-art methods in qualitative and quantitative evaluations.

Effectively captures diverse speaking styles across datasets.

Enables realistic and style-consistent facial animations.

Abstract

Speech-driven 3D facial animation aims to synthesize vivid facial animations that accurately synchronize with speech and match the unique speaking style. However, existing works primarily focus on achieving precise lip synchronization while neglecting to model the subject-specific speaking style, often resulting in unrealistic facial animations. To the best of our knowledge, this work makes the first attempt to explore the coupled information between the speaking style and the semantic content in facial motions. Specifically, we introduce an innovative speaking style disentanglement method, which enables arbitrary-subject speaking style encoding and leads to a more realistic synthesis of speech-driven facial animations. Subsequently, we propose a novel framework called \textbf{Mimic} to learn disentangled representations of the speaking style and content from facial motions by building two latent spaces for style and content, respectively. Moreover, to facilitate disentangled representation learning, we introduce four well-designed constraints: an auxiliary style classifier, an auxiliary inverse classifier, a content contrastive loss, and a pair of latent cycle losses, which can effectively contribute to the construction of the identity-related style space and semantic-related content space. Extensive qualitative and quantitative experiments conducted on three publicly available datasets demonstrate that our approach outperforms state-of-the-art methods and is capable of capturing diverse speaking styles for speech-driven 3D facial animation. The source code and supplementary video are publicly available at: https://zeqing-wang.github.io/Mimic/