演讲者：Jingyi Yu
时间：2014 年 10 月 30 日中午 12 点-1 点
地点：计算机楼 405 会议室
联系人：黄萱菁 xjhuang@fudan.edu.cn
Abstract:
A light field captures a dense set of rays as scene descriptions in place of 3D geometry. Recent advances on computational imaging have enabled novel and efficient light field acquisition devices. For example, the new Lytro and Raytrix cameras are able to capture light fields in a single shot but at a very low spatial and angular resolution. In this talk, I present several new approaches that address the resolution issue in light field imaging as well as use light field acquisition devices and post-processing algorithms for resolving traditionally challenging computer vision problems including saliency detection, dense stereo matching, and transparent object reconstruction.
Bio:
Jingyi Yu is an Associate Professor in the Department of Computer & Information Sciences and the Department of Electrical & Computer Engineering at the University of Delaware. He received his 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 cameras and displays. He has served as a Program Chair of LF4CV ’14, OMNIVIS ’11, PROCAMS ’08, and an Area and Session Chair of ICCV 11. He is a recipient of both the NSF CAREER Award and the AFOSR YIP Award. He is on the editorial board member of IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), the Visual Computer Journal, and Machine Vision and Application (MVA).
