Speaker: Prof. Kyros Kutulakos
Time: 10:30-11:30, Sep 12
Location: SIST 1A 200
Host: Prof. Jingyi Yu
Even though structured-light triangulation is a decades-old problem, much remains to be discovered about it with potential ramifications for computational imaging more broadly.I will focus on two specific aspects of the problem that are influenced by recent developments in our field. First, programmable coded-exposure sensors vastly expand the degrees of freedom of an imaging system, essentially redefining what it means to capture images under structured light. I will discuss our efforts to understand the theory and expanded capabilities of such systems, and to build custom CMOS sensors that realize them. Second, I will outline our recent work on turning structured-light triangulation into an optimal encoding-decoding problem derived from first principles. This opens the way for adaptive systems that can learn on their own how to optimally control their light sources and sensors, and how to convert the images they capture into accurate 3D geometry.
Kyros Kutulakos is a Professor of Computer Science at the University of Toronto. He received his PhD degree from the University of Wisconsin-Madison in 1994 and his BS degree from the University of Crete in 1988, both in Computer Science. Kyros has been a pioneer in the area of computational light transport, developing theoretical tools and computational cameras to analyze light propagation in real-world environments. He is the recipient of an Alfred P. Sloan Fellowship, a Marr Prize in 1999, a Marr Prize Honorable Mention in 2005 and five more paper awards (CVPR 2019, CVPR 2017, CVPR 2014, ECCV 2006 and CVPR 1994). He was Program Co-Chair of CVPR 2003 and ICCV 2013, and also served as Program Co-Chair of the Second International Conference on Computational Photography in 2010. Kyros recently arrived at ShanghaiTech and will be spending the 2019-20 academic year here, on sabbatical from the University of Toronto.