AI Paper Atlas

Research map / Video / Video generation

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

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

ECCV 2026 · Video › Video generation · approach: Talking face generation · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use Mean Flow one-step MeanTalker instead of diffusion MSMDMeanTalker · TFHP testLVE: 8.390 -> 7.879Improved
use MeanTalker instead of DiffPoseTalk for speedMeanTalker · TFHP testRTF: 0.919 -> 0.004Improved
add Geometric-Aware Trajectory Learning (GATL) over MSE-only loss (ablation)MeanTalker · TFHP testLVE: 8.735 -> 7.879Improved
add GATL over MSE-only loss (ablation)MeanTalker · TFHP testMOD: 3.187 -> 2.830Improved
add GATL over MSE-only loss (ablation)MeanTalker · TFHP testFDD: 5.152 vs 5.189No clear effect
add dual-time encoding and rectification for one-step inference (ablation)MeanTalker · TFHP testLVE: 9.189 -> 7.879Improved
add progressive initialization from pretrained standard FM (ablation)MeanTalker · TFHP testLVE: 8.272 -> 7.879Improved
add progressive initialization (convergence speed) (ablation)MeanTalker · TFHP testtraining iterations to converge: approximately 65K vs. 30K iterationsImproved
add style code (ablation)MeanTalker · TFHP testFDD: 5.919 -> 5.189Improved
add style code (ablation)MeanTalker · TFHP testLVE: 9.144 -> 7.879Improved
one-step MeanTalker vs 25-step pretrained standard FM (ablation)MeanTalker · TFHP testLVE: 8.906 -> 7.879Improved
MeanTalker vs MSMD in user study lip syncMeanTalker · TFHP user studyMOS lip sync: 3.69 -> 4.32Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy