VividAnimator: An End-to-End Audio and Pose-driven Half-Body Human Animation Framework

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Huang, Donglin, Li, Yongyuan, Liu, Tianhang, Huang, Junming, Yang, Xiaoda, Wang, Chi, Xu, Weiwei
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917005273071616
author Huang, Donglin
Li, Yongyuan
Liu, Tianhang
Huang, Junming
Yang, Xiaoda
Wang, Chi
Xu, Weiwei
author_facet Huang, Donglin
Li, Yongyuan
Liu, Tianhang
Huang, Junming
Yang, Xiaoda
Wang, Chi
Xu, Weiwei
contents Existing for audio- and pose-driven human animation methods often struggle with stiff head movements and blurry hands, primarily due to the weak correlation between audio and head movements and the structural complexity of hands. To address these issues, we propose VividAnimator, an end-to-end framework for generating high-quality, half-body human animations driven by audio and sparse hand pose conditions. Our framework introduces three key innovations. First, to overcome the instability and high cost of online codebook training, we pre-train a Hand Clarity Codebook (HCC) that encodes rich, high-fidelity hand texture priors, significantly mitigating hand degradation. Second, we design a Dual-Stream Audio-Aware Module (DSAA) to model lip synchronization and natural head pose dynamics separately while enabling interaction. Third, we introduce a Pose Calibration Trick (PCT) that refines and aligns pose conditions by relaxing rigid constraints, ensuring smooth and natural gesture transitions. Extensive experiments demonstrate that Vivid Animator achieves state-of-the-art performance, producing videos with superior hand detail, gesture realism, and identity consistency, validated by both quantitative metrics and qualitative evaluations.
format Preprint
id arxiv_https___arxiv_org_abs_2510_10269
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VividAnimator: An End-to-End Audio and Pose-driven Half-Body Human Animation Framework
Huang, Donglin
Li, Yongyuan
Liu, Tianhang
Huang, Junming
Yang, Xiaoda
Wang, Chi
Xu, Weiwei
Computer Vision and Pattern Recognition
Existing for audio- and pose-driven human animation methods often struggle with stiff head movements and blurry hands, primarily due to the weak correlation between audio and head movements and the structural complexity of hands. To address these issues, we propose VividAnimator, an end-to-end framework for generating high-quality, half-body human animations driven by audio and sparse hand pose conditions. Our framework introduces three key innovations. First, to overcome the instability and high cost of online codebook training, we pre-train a Hand Clarity Codebook (HCC) that encodes rich, high-fidelity hand texture priors, significantly mitigating hand degradation. Second, we design a Dual-Stream Audio-Aware Module (DSAA) to model lip synchronization and natural head pose dynamics separately while enabling interaction. Third, we introduce a Pose Calibration Trick (PCT) that refines and aligns pose conditions by relaxing rigid constraints, ensuring smooth and natural gesture transitions. Extensive experiments demonstrate that Vivid Animator achieves state-of-the-art performance, producing videos with superior hand detail, gesture realism, and identity consistency, validated by both quantitative metrics and qualitative evaluations.
title VividAnimator: An End-to-End Audio and Pose-driven Half-Body Human Animation Framework
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.10269