2020 年 8月 图 学 学 报 August 2020
第 41 卷 第 4 期 Jimage in RGB format. Firstly, the low-frequency
information of the image was reconstructed via U-net and then was input into the residual network to
reconstruct the high-frequency information of the image. Through the experiments carried out on the
SID data set and comparisons with previous research results, it is proved that the method described in
this paper can effectively enhance the visual effect of the images captured under extreme low-light
conditions and improved with low-light enhancement, and increase the expression of the image
details.
收稿日期:2020-01-30;定稿日期:2020-03-02
Received:30 January,2020;Finalized:2 March,2020
第一作者:杨 勇(1996),男,河南信阳人,硕士研究生。主要研究方向为计算机视觉、深度学****E-mail:******@
First author:YONG Yong (1996), male, master student. His main research interests cover computer vision, deep learning.
E-mail:******@
通信作者:刘惠义(1961),男,江苏常州人,教授,博士。主要研究方向为计算机图像学、CAD/CAM、虚拟现实、科学计算可视化。
E-mail:******@
Corresponding author:LIU Hui-yi (1961), male, professor, . His main research interests cover computer graphics, CAD/CAM, virtual reality,
visualization of scientific computation. E-mail:******@
万方数据第 4 期
极端低光情况下的图像增强方法 来自淘豆网www.taodocs.com转载请标明出处.