Spectral Modeling, Imaging and Restoration

Speaker:   Prof. Ying Fu

Time:       14:00-15:30, Nov. 3

Location:  SIST 1A 200

Host:       Prof. Jingyi Yu

Abstract:

Spectral modeling often focuses on the reflective material. In fact, it was reported that fluorescent surfaces are present in 20% of randomly constructed scenes. This is a significant proportion of scenes that have not been considered in the past. Another important point is that reflective and fluorescent components behave very differently under different illuminants. Thus, to accurately predict the color of objects, separate modeling of all spectral properties of both reflective and fluorescent components is essential. This research obviously relies on spectral imaging systems. Conventional spectral imaging systems often make the tradeoff between temporal/spatial resolution and spectral resolution. The imaging system needs to prolong the exposure time, or to reduce the spatial resolution, so as to collect enough photons to achieve a reasonable signal-to-noise ratio. This lecture will introduce the spectral modeling of reflective-fluorescent scenes, several computational spectral imaging systems and the corresponding reconstruction approaches to achieve the high-resolution spectral video in high quality.

Bio:

Ying Fu received the B.S. degree in Electronic Engineering from Xidian University in 2009, the M.S. degree in Automation from Tsinghua University in 2012, and the Ph.D. degree in Information Science and Technology from the University of Tokyo in 2015. She is currently a Professor with the School of Computer Science and Technology, Beijing Institute of Technology. Her research interests include physics-based vision, image/video processing, and computational photography. She received the Outstanding Paper Award from ICML’20, and the Best Paper Award from PRCV’19.

SIST-Seminar 18250