计算机工程与应用2019，Vol.55Issue(6)：173-177,5.DOI:10.3778/j.issn.1002-8331.1712-0048
基于生成对抗网络的运动模糊图像复原
Motion Deblurring Based on Generative Adversarial Networks
摘要
Abstract
Image motion blur is a very challenging problem caused by camera shaking or object movements. In order to tackle this problem, the paper proposes a deep convolutional neural network based on generative adversarial networks method. The proposed method can restore a clear image in an end-to-end way without estimating blur kernel. By introduc-ing adversarial loss based on generative adversarial networks and modifying the residual network structure, the proposed method can restore image details effectively. Then this paper trains this deep convolutional neural network model on pub-lic datasets. Finally, it is proved that the proposed method achieves good results according to the test on blurry image benchmark datasets.关键词
运动模糊/图像复原/生成对抗网络/深度学习Key words
motion blur/image restoration/generative adversarial networks/deep learning分类
信息技术与安全科学引用本文复制引用
桑亮,高爽,尹增山..基于生成对抗网络的运动模糊图像复原[J].计算机工程与应用,2019,55(6):173-177,5.基金项目
国家自然科学基金(No.51704115) （No.51704115）
湖南省教育厅开放基金(No.17K040,No.15K051) （No.17K040,No.15K051）
湖南省自然科学基金(No.2017JJ3099) （No.2017JJ3099）
湖南省科技计划项目(No.2016TP1021) （No.2016TP1021）
湖南省研究生科研创新项目(No.CX2017B769). （No.CX2017B769）
