期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2017
卷号：5
期号：3
页码：6057
DOI：10.15680/IJIRCCE.2017.0503363
出版社：S&S Publications
摘要：Motion blur from camera shake is a major problem in videos captured by hand held devices. Shakycameras often capture videos with motion blurs, especially when the light is insufficient. Unlike single image deblurring,video based approaches can take advantage of the abundant information that exists across neighboring frames.In this paper, we present a framework that can restore blurry frames effectively by synthesizing the details from sharpframes. Our method compares a blur patch directly against sharp candidates, in which the nearest neighbor matches canbe recovered with sufficient accuracy for the de-blurring. Moreover, to restore one blurry frame, instead of searchingover a number of nearby sharp frames, we only search from a synthesized sharp frame that is merged by differentregions from different sharp frames via an MRF-based region selection. This method achieves a very good quality withan improved efficiency and robustness.
