《计算机应用研究》|Application Research of Computers

基于ResNeXt和WGAN网络的单图像超分辨率重建

Single image super resolution based on ResNeXt and WGAN

免费全文下载 (已被下载 次)  
获取PDF全文
作者 曾庆亮,南方哲,尚迪雅,孙华
机构 新疆大学 软件学院,乌鲁木齐 830046
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2020)12-062-3815-05
DOI 10.19734/j.issn.1001-3695.2019.09.0579
摘要 为解决现有基于生成对抗网络的单图像超分辨率重建模型SRGAN网络训练不稳定、学习速率慢等问题,提出了一种基于ResNeXt和WGAN的单图像超分辨率重建模型Res_SRGAN。该模型参考ResNeXt网络结构构造生成器,降低了生成器的复杂度,仅为SRGAN的1/8;通过WGAN来构造判别器解决了SRGAN模型不稳定的问题;实验结果表明,在四个公开数据集上所提模型相较于现有单图像超分辨率重建模型在主客观评价中均取得了更加优越的性能。
关键词 单图像超分辨率重建; ResNeXt; WGAN; 深度学习
基金项目 新疆维吾尔自治区自然科学基金资助项目(2015211C263)
新疆维吾尔自治区研究生创新项目(XJ2019G069,XJ2019G072)
本文URL http://www.arocmag.com/article/01-2020-12-062.html
英文标题 Single image super resolution based on ResNeXt and WGAN
作者英文名 Zeng Qingliang, Nan Fangzhe, Shang Diya, Sun Hua
机构英文名 College of Software,Xinjiang University,Urumqi 830046,China
英文摘要 To solve the problem of unstable training and slow learning speed problems of a generative adversarial network for image super-resolution(SRGAN), the paper proposed a single image super-resolution reconstruction model called the Res_SRGAN based on ResNeXt and WGAN. The model referred to ResNeXt network structure construction generator, which reduced the computational complexity of model generator to 1/8 that of the SRGAN. The discriminator was constructed by WGAN, which solved SRGAN's instability. Experimental results demonstrate that the proposed model achieves better performance in subjective and objective evaluations using four public data sets compared with other single-image super-resolution reconstruction models.
英文关键词 single image super-resolution reconstruction; ResNeXt; Wasserstein GANC(WGAN); deep learning
参考文献 查看稿件参考文献
 
收稿日期 2019/9/27
修回日期 2019/11/18
页码 3815-3819
中图分类号 TP391.41
文献标志码 A