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：6248
DOI：10.15680/IJIRCCE.2017.0503394
出版社：S&S Publications
摘要：Motion blur from camera shake is a major problem in videos captured by hand held devices. Shaky camerasoften capture videos with motion blurs, especially when the light is insufficient. Unlike single image de-blurring, video basedapproaches can take advantage of the abundant information that exists across neighboring frames. In this paper, we present aframework that can restore blurry frames effectively by synthesizing the details from sharp frames. Our method compares ablur patch directly against sharp candidates, in which the nearest neighbor matches can be recovered with sufficient accuracyfor the de-blurring. Moreover, to restore one blurry frame, instead of searching over a number of nearby sharp frames, weonly search from a synthesized sharp frame that is merged by different regions from different sharp frames via an MRF-basedregion selection. This method achieves a very good quality with an improved efficiency and robustness.
