学术报告题目: Robust multi-frame super resolution with adaptive norm choice using difference curvature based BTV regularization

主讲人: Jiying Zhao(加拿大渥太华大学教授)

主持人：张琳教授
时  间：2018年10月10日（星期三）上午10:00

地  点： 经管楼228

摘要:

This presentation reports our research on conventional multi-frame super-resolution and deep learning based multi-frame super-resolution. Multi-frame super-resolution focuses on reconstruction of a high-resolution image from a set of low-resolution images with high similarity. The minimization function derived from maximum a posteriori probability (MAP) is composed of a fidelity term and a regularization term. In this presentation, we present a new regularization term combining the advantage of difference curvature and bilateral total variation (BTV) which keeps the edge area and removes the noise at the same time [1]. For the fidelity term in our proposed method, an adaptive norm is selected for every low-resolution image based on half-quadratic estimation to replace the traditional fixed L1 and L2 norm. Experimental results using both synthetic and real frames illustrate the superiority of our proposed method in terms of clearer texture and less noise. After that, we present our recent achievement on deep learning based multi-frame super-resolution.

[1] Xiaohong Liu, Lei Chen, Wenyi Wang, and Jiying Zhao, Robust Multi-Frame Super-Resolution Based on Spatially Weighted Half-Quadratic Estimation and Adaptive BTV Regularization, IEEE Transactions on Image Processing, vol.27, no.10, pp.4971-4986, 2018.

讲座人信息: Prof. Jiying Zhao received his B.Eng. and M.Eng. in Computer Engineering, and Ph.D. degree in Electrical Engineering from North China Electric Power University (NCEPU), China, respectively in 1983, 1988, and 1992, and his second Ph.D. degree in Engineering from Keio University, Japan, in 1998.  He worked for NCEPU as an assistant lecturer, lecturer, and associate professor from 1983 to 1994, and as an instructor and associate professor for Department of Computing Science at University College of the Cariboo (now Thompson Rivers University), Canada, from 1998 to 2001.  He joined the School of Electrical Engineering and Computer Science (EECS) at University of Ottawa as an assistant professor in 2001, became an associate professor in 2005, and then a full professor in 2009. His current research interests are on image/video processing and multimedia communications.

该讲座为前沿讲座，欢迎全校师生踊跃参加。

校学术委员会

信息与通信工程学院