Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Tianbao, Zhao, Jian, Li, Yuer, Zhu, Zheng, Hu, Ping, Fan, Zhaoxin, Wu, Wenjun, Li, Xuelong
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2505.15058
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912645344395264
author Zhang, Tianbao
Zhao, Jian
Li, Yuer
Zhu, Zheng
Hu, Ping
Fan, Zhaoxin
Wu, Wenjun
Li, Xuelong
author_facet Zhang, Tianbao
Zhao, Jian
Li, Yuer
Zhu, Zheng
Hu, Ping
Fan, Zhaoxin
Wu, Wenjun
Li, Xuelong
contents Whole-body audio-driven avatar pose and expression generation is a critical task for creating lifelike digital humans and enhancing the capabilities of interactive virtual agents, with wide-ranging applications in virtual reality, digital entertainment, and remote communication. Existing approaches often generate audio-driven facial expressions and gestures independently, which introduces a significant limitation: the lack of seamless coordination between facial and gestural elements, resulting in less natural and cohesive animations. To address this limitation, we propose AsynFusion, a novel framework that leverages diffusion transformers to achieve harmonious expression and gesture synthesis. The proposed method is built upon a dual-branch DiT architecture, which enables the parallel generation of facial expressions and gestures. Within the model, we introduce a Cooperative Synchronization Module to facilitate bidirectional feature interaction between the two modalities, and an Asynchronous LCM Sampling strategy to reduce computational overhead while maintaining high-quality outputs. Extensive experiments demonstrate that AsynFusion achieves state-of-the-art performance in generating real-time, synchronized whole-body animations, consistently outperforming existing methods in both quantitative and qualitative evaluations.
format Preprint
id arxiv_https___arxiv_org_abs_2505_15058
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AsynFusion: Towards Asynchronous Latent Consistency Models for Decoupled Whole-Body Audio-Driven Avatars
Zhang, Tianbao
Zhao, Jian
Li, Yuer
Zhu, Zheng
Hu, Ping
Fan, Zhaoxin
Wu, Wenjun
Li, Xuelong
Sound
Artificial Intelligence
Computer Vision and Pattern Recognition
Graphics
Audio and Speech Processing
68T10
Whole-body audio-driven avatar pose and expression generation is a critical task for creating lifelike digital humans and enhancing the capabilities of interactive virtual agents, with wide-ranging applications in virtual reality, digital entertainment, and remote communication. Existing approaches often generate audio-driven facial expressions and gestures independently, which introduces a significant limitation: the lack of seamless coordination between facial and gestural elements, resulting in less natural and cohesive animations. To address this limitation, we propose AsynFusion, a novel framework that leverages diffusion transformers to achieve harmonious expression and gesture synthesis. The proposed method is built upon a dual-branch DiT architecture, which enables the parallel generation of facial expressions and gestures. Within the model, we introduce a Cooperative Synchronization Module to facilitate bidirectional feature interaction between the two modalities, and an Asynchronous LCM Sampling strategy to reduce computational overhead while maintaining high-quality outputs. Extensive experiments demonstrate that AsynFusion achieves state-of-the-art performance in generating real-time, synchronized whole-body animations, consistently outperforming existing methods in both quantitative and qualitative evaluations.
title AsynFusion: Towards Asynchronous Latent Consistency Models for Decoupled Whole-Body Audio-Driven Avatars
topic Sound
Artificial Intelligence
Computer Vision and Pattern Recognition
Graphics
Audio and Speech Processing
68T10
url https://arxiv.org/abs/2505.15058