Poster Sat, Sep 12, 2026 • 1:30 AM – 3:30 AM PDT ExHall # 135

MeanTalker: Efficient and Expressive Speech-Driven 3D Facial Animation via Geometric-Aware Mean Flow

Zhongyuan Zhao ⋅ Zhihao Li ⋅ Qing Li ⋅ Leidong Fan ⋅ KANGLIN LIU

Keywords: Low-Level Vision, Restoration & Generative Priors