Statistical Blendshape Calculation and Analysis for Graphics Applications

Real-time facial avatar animation is widely used in entertainment, office and other fields where blendshapes have become a common animation method. We independently developed an accurate blend-shape prediction system for low-power VR applications using a webcam. Feature vectors are extracted through affine transformation and segmentation. Further transformation and regression analysis was used to develop statistical models with significant predictive power. Post-processing was used to further improve response stability, including smoothing filtering and nonlinear transformations. The system achieved accuracy similar to ARKit 6.