Xiaoming Liu – 2D/3D Shape Estimation and Recognition for Large-pose Faces
This talk covers two areas of research on facial analysis: face shape recovery via deformable model fitting, and large-pose face recognition. We start by presenting two lines of research that focus on estimating the 2D and 3D facial shape from unconstrained photos, respectively. We achieve 2D facial shape estimation by face alignment. Specifically, we develop a pose-invariant face alignment method that can align faces with arbitrary poses, by fitting a 3D face model via CNN. We will also present a photometric stereo-based algorithm for unconstrained 3D face reconstruction – 3D facial shape estimation. In the second area of large-pose face recognition, we present two learning-based approaches. One is to use novel Generative Adversarial Network to simultaneously learn pose-invariant identity features and synthesize face images with arbitrary pose. The other is to design Multi-Task CNN to improve face recognition under pose, illumination and expression variations.
Xiaoming Liu is an Assistant Professor at the Department of Computer Science and Engineering of Michigan State University. He received the Ph.D. degree in Electrical and Computer Engineering from Carnegie Mellon University in 2004. Before joining MSU in Fall 2012, he was a research scientist at General Electric (GE) Global Research. His research interests include computer vision, patter recognition, biometrics and machine learning. As a co-author, he is a recipient of Best Industry Related Paper Award runner-up at ICPR 2014, Best Student Paper Award at WACV 2012 and 2014, and Best Poster Award at BMVC 2015. He has been the Area Chair for numerous conferences, including FG, ICPR, WACV, and CVPR. He has authored more than 100 scientific publications, and has filed 22 U.S. patents.