摘要
针对超分辨率重建算法效率低以及对高频信息重建力度不足等问题,采用低秩分解方法,将图像分解后单独重建,并在此基础上加入图像的残差信息对重建图像进行高频增强,从而提出了一种新的双层重建算法.实验结果表明,算法在性能和效率方面均有大幅度提升.
In view of the low efficiency and insufficient ability to reconstruct high frequency information of super resolution reconstruction approaches,a low rank decomposition algorithm is used to decompose the image and reconstruct each part separately in this paper.On this basis,a novel double-layered reconstruction scheme is proposed,adding the residual information of the image to enhance the reconstructed image.The experimental results show that the performance and efficiency of the proposed approach are greatly improved.
作者
高冉
王赟
GAO Ran;WANG Yun(College of Science,Zhongyuan University of Technology,Zhengzhou 450007,China)
出处
《数学的实践与认识》
北大核心
2020年第23期129-140,共12页
Mathematics in Practice and Theory
基金
国家自然科学基金(11601542,11801133)
河南省科技攻关项目(182102210524)
河南省教育厅重点研究项目(17A110036)。
关键词
超分辨率重建
低秩分解
残差信息
双层
高频增强
super resolution reconstruction
low rank decomposition
double-layered
residual information
high frequency enhancement
