Visit ShanghaiTech University | 中文 | How to find us
HOME > News and Events > Events
Physics Based Vision meets Deep Learning
Date: 2018/4/16             Browse: 31

Speaker:     Dr. Shaodi You, ANU

Time:          10:00—11:30, Apr 16

Location:    Room 1A-200, SIST Building

Host:          Prof. Laurent Kneip


Light traveling in the 3D world interacts with the scene through intricate processes before being captured by a camera. Physics based vision aims to invert the processes to recover the scene properties, such as shape, reflectance, light distribution, medium properties, etc., from images. In recent years, deep learning shows promising improvement for various vision tasks.

When physics based vision meets deep learning, there will be mutual benefits. On one hand, classic physics-based vision tasks can be implemented in a data-fashion way to handle complex scenes. This is because, physically more accurate optical models can be too complex to be solved (usually too many unknown parameters in one model). These intrinsic physical properties potentially can be learned through deep learning. On the other hand, deep learning methods should consider physics principles in the modelling and computation, since the models can provide strong constraints and rich knowledge about the real world.


Dr. Shaodi You is a senior research scientist at Data61, (Previously known as NICTA) Canberra Research Lab and a senior adjunct lecturer of College of Engineering and Computer Science at Australian National University (ANU). He receives his Ph.D. and M.E. degrees from The University of Tokyo, Japan in 2015 and 2012 and his bachelor's degree from Tsinghua University, P. R. China in 2009. His research interests are 1. physics based vision, 2. perception based vision and learning, and 3. 3D geometry.

SIST-Seminar 18019