2019年10月13日下午15:30，信息楼119
Prof. Ce ZHU, University of Electronic Science & Technology of China Ce Zhu is currently a Professor with the School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China. His research interests include image/video coding and communications, video analysis and processing, 3D video, visual perception and applications. He has served on the editorial boards of a few journals, including as an Associate Editor of IEEE Transactions on Image Processing, IEEE Transactions on Circuits and Systems for Video Technology, IEEE Transactions on Broadcasting, and IEEE Signal Processing Letters. He has served on technical committees, organizing committees and as track/area/session chairs for over 60 international conferences, including serving as a Technical Program Co-Chair of IEEE ICME 2017. He is a Fellow of the IEEE and a Fellow of the IET. For more information, please visit his homepage at http://www.avc2-lab.net/~eczhu
Speech Title: Deep Learning for In-Loop Filter Design in HEVC
Abstract: In-loop filters have been employed to reduce coding artifacts in the recent video coding standards including the latest High Efficiency Video Coding (HEVC) standard. However, in the existing approaches, an in-loop filter is always applied to each single frame, without exploiting the content correlation among multiple frames. In the talk, we introduce a multiframe in-loop filter (MIF) for HEVC, which enhances the visual quality of each encoded frame by leveraging its adjacent frames. Extensive experiments show that the MIF approach achieves 11.621% saving of the Bjøntegaard delta bit-rate (BDBR) on the test set, significantly outperforming the standard in-loop filter in HEVC and other state-ofthe-art approaches. The talk is based on our recent work entitled “A Deep Learning Approach for MultiFrame In-Loop Filter of HEVC” in IEEE Transactions on Image Processing (in press, https://github.com/tianyili2017/HIF-Database).