Audio2Face-3D: Audio-driven Realistic Facial Animation For Digital Avatars

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: NVIDIA, :, Chung, Chaeyeon, Fedorov, Ilya, Huang, Michael, Karmanov, Aleksey, Korobchenko, Dmitry, Ribera, Roger, Seol, Yeongho
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914000979099648
author NVIDIA
:
Chung, Chaeyeon
Fedorov, Ilya
Huang, Michael
Karmanov, Aleksey
Korobchenko, Dmitry
Ribera, Roger
Seol, Yeongho
author_facet NVIDIA
:
Chung, Chaeyeon
Fedorov, Ilya
Huang, Michael
Karmanov, Aleksey
Korobchenko, Dmitry
Ribera, Roger
Seol, Yeongho
contents Audio-driven facial animation presents an effective solution for animating digital avatars. In this paper, we detail the technical aspects of NVIDIA Audio2Face-3D, including data acquisition, network architecture, retargeting methodology, evaluation metrics, and use cases. Audio2Face-3D system enables real-time interaction between human users and interactive avatars, facilitating facial animation authoring for game characters. To assist digital avatar creators and game developers in generating realistic facial animations, we have open-sourced Audio2Face-3D networks, SDK, training framework, and example dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16401
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Audio2Face-3D: Audio-driven Realistic Facial Animation For Digital Avatars
NVIDIA
:
Chung, Chaeyeon
Fedorov, Ilya
Huang, Michael
Karmanov, Aleksey
Korobchenko, Dmitry
Ribera, Roger
Seol, Yeongho
Graphics
Human-Computer Interaction
Machine Learning
Sound
Audio and Speech Processing
Audio-driven facial animation presents an effective solution for animating digital avatars. In this paper, we detail the technical aspects of NVIDIA Audio2Face-3D, including data acquisition, network architecture, retargeting methodology, evaluation metrics, and use cases. Audio2Face-3D system enables real-time interaction between human users and interactive avatars, facilitating facial animation authoring for game characters. To assist digital avatar creators and game developers in generating realistic facial animations, we have open-sourced Audio2Face-3D networks, SDK, training framework, and example dataset.
title Audio2Face-3D: Audio-driven Realistic Facial Animation For Digital Avatars
topic Graphics
Human-Computer Interaction
Machine Learning
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2508.16401