=======
We propose a novel PointNet-based encoder-decoder framework that for the first time jointly learns an expressive face model from a diverse set of raw 3D scans and establishes dense correspondence among them.
=======
3D Face Modeling from Diverse Raw Scan Data. ICCV 2019. Paper
Feng Liu, Luan Tran, Xiaoming Liu
Department of Computer Science and Engineering, Michigan State University.