报告时间：2018年8月1日（星期三）下午14：00
报告地点：浙江大学紫金港校区蒙民伟楼402会议室
报告人：Zihan Zhou 助理教授
主持人：章国锋 教授

Title:Learning to Discover Structure for 3D Computer Vision

Abstract:Although significant progress has been made about the imaging devices and 3D reconstruction techniques over the past few decades, obtaining accurate 3D models and the associated camera positions from images still remains a challenging problem in computer vision. Moreover, when directly utilized in real-world applications, existing methods often lead to unsatisfactory performances in terms of reliability, applicability, and scalability.
In this talk, I argue that much of the difficulties faced by the current techniques and applications can be alleviated by harnessing various forms of global spatial relationships in the scene, such as parallel lines, planar surfaces, and repetitive patterns. Specifically, I describe novel deep learning methods to discover such geometric structures from images, and demonstrate how to utilize them for robust and efficient 3D reconstruction. As an ongoing research effort, I will also discuss new opportunities and challenges in exploiting global structures in large-scale visual data for emerging commercial and customer applications, such as architectural design, VR/AR, and autonomous driving.

Bio:Zihan Zhou is an assistant professor in the College of Information Sciences and Technology at The Pennsylvania State University. Before joining Penn State, he completed his Ph.D in Electrical and Computer Engineering at the University of Illinois at Urbana-Champaign in 2013. His research interest lies in the broad area of computer vision, machine learning, signal processing, and applied data sciences, with a focus on developing new computational tools to model and analyze the 3D environments from big visual data, and apply them to solve challenging real-world problems in VR/AR, vision-based navigation, architectural design and engineering, social media, and more. To learn more, please visit his homepage: https://faculty.ist.psu.edu/zzhou