•   When: Monday, February 08, 2021 from 11:00 AM to 12:00 PM
•   Speakers: Yiming Qian, Postdoctoral researcher at Simon Fraser University, Canada
•   Location: ZOOM
•   Export to iCal

Abstract: Humans are remarkably good at understanding and operating in the three-dimensional (3D) world. Computer vision research aims to provide such human-like perception to machines, which primarily relies on three important ingredients: robust data acquisition devices, reliable physics-based rules, and effective data-driven models. In this talk, I will focus on how to utilize these elements for 3D shape reconstruction and generation. Specifically, I will present a physics-based method for reconstructing transparent objects by introducing a novel data acquisition setup. Besides, I will present a data-driven learning-based method for generating realistic 3D residential houses.

Bio: Yiming Qian is a postdoctoral researcher at Simon Fraser University, Canada. His research interests lie at the intersection of computer graphics and computer vision. His current research focuses on the reconstruction and generation of 3D environments by combining advances in physics, geometry, imaging, and deep learning. He completed his Ph.D. in Computer Science at the University of Alberta, Canada. He was the recipient of the best paper award at the 2015 Canadian Conference on Artificial Intelligence.