时间：2014年6月16日下午13:30
地点：浙大紫金港校区CAD&CG国家重点实验室402室
主持：周昆  教授
Title：3D Reconstruction of "Invisible" Objects
Abstract: The problem of modeling and reconstructing ``invisibles" phenomena such as specular or transparent 3D fluid wavefront and gas flows has attracted much attention in recent years. The problem is inherently challenging since such objects do not have their own image but borrow appearance from nearby diffuse objects. In this talk, I present a class of computational imaging approaches for transparent object reconstructions by acquiring ray-ray correspondences. Specifically, I exploit an emerging class of light field cameras and displays. Specifically, I present three solutions: a light field camera array for recovering transparent wavefront, a Bokode system for reconstructing transparent objects, and a light field probe solution for recovering volumetric 3D gas flows. Comprehensive experiments on synthetic and real data demonstrate that our new computational imaging approaches are reliable, robust, and accurate.
Bio: Jingyi Yu is an Associate Professor in the Department of Computer and Information Sciences and the Department of Electrical and Computer Engineering at the University of Delaware. He received B.S. from Caltech in 2000 and Ph.D. from MIT in 2005. His research interests span a range of topics in computer vision and computer graphics, especially on computational photography and non-conventional optics and camera designs. He has by far published over 90 articles including 40 papers at the premiere computer vision conferences CVPR/ICCV/ECCV. His research has been generously supported by the National Science Foundation (NSF), the National Institute of Health (NIH), the Army Research Office (ARO), and the Air Force Office of Scientific Research (AFOSR). He is a recipient of the NSF CAREER Award and the AFOSR Young Investigator Award.