Livatar-1：使用定制 Flow Matching 的实时说话人头像生成
Livatar-1: Real-Time Talking Heads Generation with Tailored Flow Matching
AI总结：
提出音频驱动的实时说话人头像框架 Livatar，通过定制 flow matching 与系统优化改善唇形同步和姿态漂移，并在 HDTF 与单张 A10 GPU 上实现高质量、低延迟生成。
摘要：
我们提出 Livatar，这是一个实时的音频驱动说话人头像视频生成框架。现有基线存在唇形同步准确性有限和长期姿态漂移的问题。我们通过一个基于 flow matching 的框架解决这些局限。结合系统优化，Livatar 在 HDTF 数据集上取得具有竞争力的唇形同步质量，LipSync Confidence 为 8.50；并在单张 A10 GPU 上达到 141 FPS 的吞吐量和 0.17 秒的端到端延迟。这使高保真虚拟形象可用于更广泛的应用。我们的项目可在 https://www.hedra.com/ 获取，示例位于 https://h-liu1997.github.io/Livatar-1/。
英文摘要：
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/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
