Saved in:
Bibliographic Details
Main Authors: Liu, Haiyang, Hong, Xiaolin, Yang, Xuancheng, Ruan, Yudi, Lian, Xiang, Lingelbach, Michael, Yi, Hongwei, Li, Wei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.18649
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911075573694464
author Liu, Haiyang
Hong, Xiaolin
Yang, Xuancheng
Ruan, Yudi
Lian, Xiang
Lingelbach, Michael
Yi, Hongwei
Li, Wei
author_facet Liu, Haiyang
Hong, Xiaolin
Yang, Xuancheng
Ruan, Yudi
Lian, Xiang
Lingelbach, Michael
Yi, Hongwei
Li, Wei
contents We present Livatar, a real-time audio-driven talking heads videos generation framework. Existing baselines suffer from limited lip-sync accuracy and long-term pose drift. We address these limitations with a flow matching based framework. Coupled with system optimizations, Livatar achieves competitive lip-sync quality with a 8.50 LipSync Confidence on the HDTF dataset, and reaches a throughput of 141 FPS with an end-to-end latency of 0.17s on a single A10 GPU. This makes high-fidelity avatars accessible to broader applications. Our project is available at https://www.hedra.com/ with with examples at https://h-liu1997.github.io/Livatar-1/
format Preprint
id arxiv_https___arxiv_org_abs_2507_18649
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Livatar-1: Real-Time Talking Heads Generation with Tailored Flow Matching
Liu, Haiyang
Hong, Xiaolin
Yang, Xuancheng
Ruan, Yudi
Lian, Xiang
Lingelbach, Michael
Yi, Hongwei
Li, Wei
Computer Vision and Pattern Recognition
We present Livatar, a real-time audio-driven talking heads videos generation framework. Existing baselines suffer from limited lip-sync accuracy and long-term pose drift. We address these limitations with a flow matching based framework. Coupled with system optimizations, Livatar achieves competitive lip-sync quality with a 8.50 LipSync Confidence on the HDTF dataset, and reaches a throughput of 141 FPS with an end-to-end latency of 0.17s on a single A10 GPU. This makes high-fidelity avatars accessible to broader applications. Our project is available at https://www.hedra.com/ with with examples at https://h-liu1997.github.io/Livatar-1/
title Livatar-1: Real-Time Talking Heads Generation with Tailored Flow Matching
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.18649