Papers
arxiv:2604.23692

Personalizing Causal Audio-Driven Facial Motion via Dynamic Multi-modal Retrieval

Published on Apr 26
Authors:
,
,
,

Abstract

Audio-driven facial animation is essential for immersive digital interaction, yet existing frameworks fail to reconcile real-time streaming with high-fidelity personalization. Current methods often rely on latency-inducing audio look-ahead, or require high user compliance to pre-encode static embeddings that fails to capture dynamic idiosyncrasies. We present an end-to-end causal framework for personalizing causal facial motion generation via dynamic multi-modal style retrieval, enabling ultra-low latency while uniquely leveraging unstructured style references. We introduce two key innovations: (1) a temporal hierarchical motion representation that captures global temporal context and high-frequency details while maintaining decoding causality, and (2) a multi-modal style retriever that jointly queries audio and motion to dynamically extract stylistic priors without breaking causality. This mechanism allows for scalable personalization with total flexibility regarding the number and contents of templates. By integrating these components into a causal autoregressive architecture, our method significantly outperforms state-of-the-art approaches in lip-sync accuracy, identity consistency, and perceived realism, supported by extensive quantitative evaluations and user studies.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2604.23692
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2604.23692 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2604.23692 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.