Oliver Cossairt is an Assistant Professor at Northwestern University. Before joining Northwestern, Oliver spent one year as a Postdoctoral Researcher at Columbia University, under the supervision of Professor Shree K. Nayar. His research interests lie at the intersection of optics, computer vision, and computer graphics. He earned his Ph.D. in Computer Science from Columbia University, where his research focused on the design and analysis of computational imaging systems. He earned his M.S. from the MIT Media Lab, where his research focused on holography and computational displays. Oliver was awarded a NSF Graduate Research Fellowship, Best Paper Award at ICCP 2010, and his research was featured in the March 2011 issue of Scientific American Magazine. Oliver has authored ten patents on various topics in computational imaging and displays.
My research is in the emerging field of computational imaging, which combines expertise in optics, image processing, computer vision, and computer graphics. I design, model and build systems that combine sensors, displays, and novel optical elements. These cameras have applications in medical, astronomical, and scientific imaging. I am building a new breed of cameras with increased functionality and performance. I believe that my research will impact the way cameras are built in coming decades, from low-end consumer cameras to high-end scientific instruments. A few of my recent research projects include:Extended Depth of Field [Cossairt et al. ICCP 2009 (best paper), SIGGRAPH 2010], Gigapixel Imaging [Cossairt et al. ICCP 2011, JOSA 2011a], and Analysis on Computational Imaging [Cossairt et al., TIP 2012 (accepted)].
I am fascinated with the idea that cameras can be very finely tuned towards specific purposes, and that doing so can be an excellent way to capture specific visual information. We can place the camera at the center of a larger visual processing system whose purpose is to analyze and interpret visual information. As such, the camera cannot be designed without keeping the entire system in mind. I find it interesting to consider how special purpose cameras can be extended to other domains. Can we build a camera that is tuned to recognize faces? To track moving cars? To recognize materials?