Title: 3D Vision: From 3D Modeling to Object Recognition
Time：10:30 AM, 21 December, 2017
With the rapid development of 3D data acquisition sensors, 3D vision has attracted increasing attention in recent years. Compared to 2D images, 3D point clouds can provide richer geometry, shape and structural information, and consequently offer new opportunities for scene understanding. 3D vision has numerous applications in related areas such as autonomous driving, robotics, AR/VR, and remote sensing. In this talk, I will introduce our recent progresses in depth estimation, point cloud feature representation, 3D modeling, and 3D object recognition.
Yulan Guo received his B.Eng. and Ph.D. degrees from National University of Defense Technology (NUDT) in 2008 and 2015, respectively. He is currently an assistant professor with the College of Electronic Science, NUDT. He also works as a research fellow with the Institute of Computing Technology, Chinese Academy of Sciences. He was a visiting PhD student at the University of Western Australia from 2011 to 2014. His current research focuses on 3D vision, particularly on 3D feature learning, 3D modeling, and 3D object recognition. He has authored more than 50 papers in high-ranking journals and conferences (e.g., TPAMI, IJCV). He organized a tutorial in CVPR 2016, served as a reviewer for more than 30 international journals (e.g., PAMI, IJCV), and as a PC member for several prestigious conferences (e.g., IJCAI, AAAI). He received the CAAI Distinguished PhD Thesis award and the PLA Distinguished PhD Thesis award in 2016.