学　术

　　人力资源部教师发展中心开展“名师讲堂”系列活动，以定期邀请国内外知名专家学者、国家级教学名师等作专题报告，旨在加强广大师生的学术思想交流和碰撞，促进青年教师成长，开拓学生视野。

　　“名师讲堂”第43期和第44期活动特别邀请IEEE Fellow、法国国家科研中心的Frederic Dufaux教授主讲，欢迎广大师生参与。具体安排如下：

　　第43期讲堂：

　　主　题：High Dynamic Range Video: recent research activities and perspectives

　　时　间：2016年10月24日（周一）14：30

　　地　点：清水河校区科研楼KC218  

　　主讲人：IEEE Fellow　Frederic Dufaux教授

　　内容简介：

　　Producing truly realistic video is widely seen as the holy grail towards further improving Quality of Experience (QoE) for end users of multimedia services. Several new approaches have been proposed and often successfully implemented in history of applications that use video data. Currently investigated directions include high spatial resolutions, high frame rates, wide color gamut and high bit-depth rendering.

　　The human visual system is able to perceive a wide range of colors and luminous intensities, as present in outdoor scenes in everyday real life, ranging from bright sunshine to dark shadows. However, current traditional imaging technologies cannot capture nor reproduce such a broad range of luminance. The objective of High Dynamic Range (HDR) imaging is to overcome these limitations, hence leading to more realistic videos and a greatly enhanced user experience.

　　HDR applied to still images has been an active field of research and development for many years, especially for photography. However, its extension to video content has only been considered recently. The effective deployment of HDR video technologies involves redefining common interfaces for end-to-end content delivery, which in turn, entails many technical and scientific challenges.

　　In this talk, I will first introduce the challenges arising with HDR video. I will then present some of our recent research activities covering several aspects of an HDR video system:

　　·video coding: scheme based on layered coding

　　·video analysis: how to effectively exploit the extra information in HDR content

　　·perceptual quality assessment: subjective and objective measure of the visual quality

　　第44期讲堂：

　　主　题：From multi-view video to light field representation

　　时　间：2016年10月26日（周三）14：30

　　地　点：清水河校区品学楼B109

　　主讲人：IEEE Fellow　Frederic Dufaux教授

　　内容简介：

　　Throughout the years, the Moving Picture Experts Group (MPEG) has specified a number of standards for the coding of 3D video. The recent MV-HEVC is a multi-view coding extension of HEVC enabling the compression of camera views. However, it fails to facilitate the synthesis of intermediate views. To address this limitation, the depth-based 3D-HEVC has also been developed. By supporting Depth-Image-Based Rendering (DIBR), it allows for the generation of additional views from a small set of coded views. 3D-HEVC is therefore suitable for auto-stereoscopic 3D display with tens of output views. Nevertheless, these standards assume a linear and narrow baseline arrangement of camera inputs.

　　MPEG is now exploring the standardization of Free-viewpoint TV (FTV). With FTV, the user is able to navigate the scene by freely varying the viewpoint. FTV can therefore be seen as the ultimate 3D-TV experience, providing a realistic glass-free 3D video viewing while avoiding visual fatigue.

　　In this presentation, I will first review 3D video data formats and existing MPEG 3D video coding standards. In a second part, I will then discuss on-going research activities and present some recent results.

　　主讲人简介：

　　Dr. Frederic Dufaux is a CNRS Research Director at Telecom ParisTech. He is also Editor-in-Chief of Signal Processing: Image Communication.

　　Frederic received his M.Sc. in physics and Ph.D. in electrical engineering from EPFL in 1990 and 1994 respectively. He has over 20 years of experience in research, previously holding positions at EPFL, Emitall Surveillance, Genimedia, Compaq, Digital Equipment, and MIT. He has been involved in the standardization of digital video and imaging technologies, participating both in the MPEG and JPEG committees. He is the recipient of two ISO awards for his contributions.

　　Frederic is a Fellow of IEEE. He was Vice General Chair of ICIP 2014. He is an elected member of the IEEE Image, Video, and Multidimensional Signal Processing (IVMSP) and Multimedia Signal Processing (MMSP) Technical Committees. He is the Chair of the EURASIP Special Area Team on Visual Information Processing.

His research interests include image and video coding, distributed video coding, 3D video, high dynamic range imaging, visual quality assessment, video surveillance, privacy protection, image and video analysis, multimedia content search and retrieval, and video transmission over wireless network. He is the author or co-author of 3 books, more than 120 research publications and 17 patents issued or pending.

　　主持人：电子工程学院　朱策教授

　　主办单位：人力资源部教师发展中心

　　承办单位： 电子工程学院、机器人中心

　　　　　　　　　　　　　　　　　　　　　人力资源部教师发展中心

　　　　　　　　　　　　　　　　　　　　　　　2016年10月18日