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

NVIDIA, :, Chaeyeon Chung, Ilya Fedorov, Michael Huang +4 more
8/22/2025
cs.GRcs.HCcs.LG

No confident code implementation found for this paper. 2 possible matches can be shown below.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 2 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Audio Driven Real-Time Facial Animation for Social Telepresence

85% match2025

Audio2Rig: Artist-oriented deep learning tool for facial animation

83% match2024

GaussianSpeech: Audio-Driven Gaussian Avatars

82% match1 repo1922024

3DXTalker: Unifying Identity, Lip Sync, Emotion, and Spatial Dynamics in Expressive 3D Talking Avatars

82% match2026

READ Avatars: Realistic Emotion-controllable Audio Driven Avatars

82% match2023

Universal Facial Encoding of Codec Avatars from VR Headsets

82% match2024

Cite this paper

@article{nvidia2025audiofaced,
  title  = {Audio2Face-3D: Audio-driven Realistic Facial Animation For Digital Avatars},
  author = {NVIDIA and : and Chaeyeon Chung and Ilya Fedorov and Michael Huang and Aleksey Karmanov and Dmitry Korobchenko and Roger Ribera and Yeongho Seol},
  year   = {2025},
  eprint = {2508.16401},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2508.16401v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2508.16401.svg)](https://codeofpaper.com/paper/2508.16401)

Discussion