题目：Towards Smart Imaging and Sensing: Gigapixel Videography and 3D Reconstruction
时间：下午16:00pm - 17:30pm
摘要：Smart imaging Lab aims to integrate optics, signal processing, optimization and machine learning together to explore new computational photography theories and key computational techniques to break through some deep-rooted assumptions and physical limitations in conventional imaging and sensing of 7-dimensional plenoptic data. We study the intrinsic representation of cross-dimensional visual data and reveal the redundancy and sparsity in such visual big data. This talk will start with the acquisition of extremely high resolution in spatial domain from both micro and macro aspects, i.e., Multi-Dimension Multi-Scale High-Resolution Computational Instrument, and Multiscale Camera Array for Gigapixel Videography, respectively. For the view dimensional acquisition, depth information of the scene can also be obtained to enable our recent work on Multi-view Perception and Real-time 3D Reconstruction of dynamic scenes. Finally, this talk will summarize the key technologies for future works, such as multiscale hybrid camera array design and deep leaning based plenoptic reconstruction etc.
个人介绍：Dr. Lu FANG is currently an Associate Professor in Tsinghua-Berkeley Shenzhen Institute (TBSI). She received Ph.D in Electronic and Computer Engineering from Hong Kong University of Science and Technology in 2011, and B.E. from University of Science and Technology of China in 2007, respectively. Dr. Fang's research interests are computational photography and visual computing, including Gigapixel Videography, Multi-Camera Array System, Multi-View Perception and 3D Reconstruction etc. Dr. Fang used to receive NSFC Excellent Young Scholar Award, Best Student Paper Award in ICME 2017, Finalist of World's First 10K Best Paper Award in ICME 2017, Finalist of Best Paper Award in ICME 2011 etc. Dr. Fang is currently IEEE Senior Member, and she serves as Guest Editor for IEEE JSTSP, area chair for IEEE ICIP and ICME.