Ex-Omni: Enabling 3D Facial Animation Generation for Omni-modal Large Language Models

TL;DR

Ex-Omni introduces a framework that enhances large language models with speech-driven 3D facial animation, addressing representation challenges and enabling natural multimodal interactions.

Contribution

It proposes a novel decoupling approach using speech units and a token-as-query fusion mechanism to improve 3D facial animation in large language models.

Findings

Ex-Omni achieves competitive performance with existing models.

The framework enables stable, aligned speech and facial animation generation.

InstructEx dataset facilitates training and evaluation of speech-driven 3D facial animation.

Abstract

Omni-modal large language models (OLLMs) aim to unify multimodal understanding and generation, yet incorporating speech with 3D facial animation remains largely unexplored despite its importance for natural interaction. A key challenge arises from the representation mismatch between discrete, token-level semantic reasoning in LLMs and the dense, fine-grained temporal dynamics required for 3D facial motion, which makes direct modeling difficult to optimize under limited data. We propose Expressive Omni (Ex-Omni), an open-source omni-modal framework that augments OLLMs with speech-accompanied 3D facial animation. Ex-Omni reduces learning difficulty by decoupling semantic reasoning from temporal generation, leveraging speech units as temporal scaffolding and a unified token-as-query gated fusion (TQGF) mechanism for controlled semantic injection. We further introduce InstructEx, a dataset aims to facilitate augment OLLMs with speech-accompanied 3D facial animation. Extensive experiments demonstrate that Ex-Omni performs competitively against existing open-source OLLMs while enabling stable aligned speech and facial animation generation.