CIS Colloquium, Nov 15, 2013, 11:00AM - 12:00PM, Wachman 1015D
Information-Driven Imaging for Appearance Capture and Recognition
Jinwei Gu, Rochester Institute of Technology
One of the fundamental problems in imaging, computer vision, and visualization is the study of appearance. Despite of tremendous success, the popular data - driven approach is soon becoming incompetent for the study of many high - dimensional appearance phenom ena, such as high - speed motion, light fields, and spectral images. In this talk, I argue that a better way to tackle high - dimensional appearance is th e information - driven approach. It has three key distinctions compared to the data - driven approach. (1) Phys ics - based appearance models and statistical priors of natural images should be actively incorporated to better constrain ill - posed problems. As an example, I will show how we designed algorithms to remove image artifacts caused by dirty lenses and thin occ luders from videos. (2) Instead of passively recording 2D slices of appearance (which is both expensive and redundant), novel imaging systems can be designed to take code d , informatio n - condensed projections , which can later be decoded computationally. In p articular, I will describe how we designed coded exposure for CMOS image sensors for flexible space - time sampling and motion detection. (3) Low - level image acquisition should be directly connected with high - level tasks such as detection and recognition in order to measure low - dimensional, representative features. As an example, I will describe how we learned discriminative illumination for raw material classification .
Jinwei Gu is currently a computer scientist in the Center for Vision Technologies at SRI International (Sarnoff). From 2010 to 2013, He was an assistant professor in the Munsell Color Science Laboratory in the Center for Imaging Science at Rochester Instit ute of Technology. He received his PhD degree from Columbia University in May 2010, and his bachelor and master degree from Tsinghua University, China in 2002 and 2005. His research interests are computer vision and computer graphics. His current research focuses on computational photography, physics - based computer vision, and data - driven computer graphics.