【学术报告】Advances in Image Deblurring

发稿时间:2009-12-25浏览次数:1389

NSTForum-2009032-软件新技术讲坛

香港中文大学 计算机科学与工程系 贾佳亚教授

题目:Advances in Image Deblurring
时间:28号上午10:00-11:00
地点:蒙民伟楼311室

Title: Advances in Image Deblurring
 
Abstract: One of the most common artifacts in digital photography is motion blur caused by camera shake. In many situations there simply is not enough light to avoid using a long shutter speed, and the inevitable result is that many of our snapshots come out blurry and disappointing. Recovering an un-blurred image from a single, motion-blurred photograph has long been a fundamental research problem in digital imaging. In this talk, I will introduce two recent techniques to solve this challenging problem. One method computes a deblurred image using a unified probabilistic model of both blur kernel estimation and unblurred image restoration. The other one estimates these unknowns with the color blending information.
 
 
BIOGRAPHY:
 
Prof. Jiaya Jia is now an assistant professor in the Chinese University of Hong Kong.  He was a visiting scholar in Microsoft Research Asia and Adobe research lab in 2004 and 2007. His research interest includes image analysis and enhancement, motion estimation, and 3D reconstruction. He served on the program committees of the International Conference on Computer Vision (ICCV), Computer Vision and Pattern Recognition (CVPR), European Conf. Computer Vision (ECCV) and chaired the Workshop on Interactive Computer Vision 2007. He received the Young Researcher Award 2008.