3月29号下午2:00在宝山校区翔英大楼808会议室，法国雷恩第一大学 Olivier Le Meur 副教授来访上海大学通信与信息工程学院图像与视频处理实验室（IVP），并做了名为"Global minimization energy for examplar-based image and video inpainting"的学术报告。通信学院刘志、孙广玲、王向阳老师和部分研究生参加了这次讲座。

摘要：
In this presentation, we detail two methods for filling in missing areas in an image or in vide-o sequence. The former, working on still color images, consists in inpainting several times on a low-resolution version of the input image. Results are fused together by minimizing a glob-al energy in order to provide a robust inpainted low-frequency image. A single-image super-resolution is then applied to compute the final result. Regarding the video inpainting, the pro-posed method consists in performing the registration of frames contained in a short-term te-mporal windows. From the aligned frames, the missing areas are inpainted by minimizing a global energy.

简介：
Olivier Le Meur received the Ph.D. degree from University of Nantes, Nantes, France, in 2005. He was with the Media and Broadcasting Industry from 1999 to 2009. In 2003, he joined the Research Center of Thomson-Technicolor, Rennes, France, where he supervised a Research Project concerning the modeling of human visual attention. He has been an Associate Professor of image processing with the University of Rennes 1 since 2009. He currently works at the SIROCCO Team of IRISA/INRIA-Rennes, and his current research interests include human visual attention, computational modeling of visual attention, and saliency-based applications, such as video compression, objective assessment of video quality, and retargeting.