期刊检索

  • 2024年第56卷
  • 2023年第55卷
  • 2022年第54卷
  • 2021年第53卷
  • 2020年第52卷
  • 2019年第51卷
  • 2018年第50卷
  • 2017年第49卷
  • 2016年第48卷
  • 2015年第47卷
  • 2014年第46卷
  • 2013年第45卷
  • 2012年第44卷
  • 2011年第43卷
  • 2010年第42卷
  • 第1期
  • 第2期

主管单位 中华人民共和国
工业和信息化部
主办单位 哈尔滨工业大学 主编 李隆球 国际刊号ISSN 0367-6234 国内刊号CN 23-1235/T

期刊网站二维码
微信公众号二维码
引用本文:张杨忆,林泓,管钰华,刘春.改进残差块和对抗损失的GAN图像超分辨率重建[J].哈尔滨工业大学学报,2019,51(11):128.DOI:10.11918/j.issn.0367-6234.201812115
ZHANG Yangyi,LIN Hong,GUAN Yuhua,LIU Chun.GAN image super-resolution reconstruction model with improved residual block and adversarial loss[J].Journal of Harbin Institute of Technology,2019,51(11):128.DOI:10.11918/j.issn.0367-6234.201812115
【打印本页】   【HTML】   【下载PDF全文】   查看/发表评论  下载PDF阅读器  关闭
过刊浏览    高级检索
本文已被:浏览 1628次   下载 1011 本文二维码信息
码上扫一扫!
分享到: 微信 更多
改进残差块和对抗损失的GAN图像超分辨率重建
张杨忆,林泓,管钰华,刘春
(武汉理工大学 计算机科学与技术学院,武汉 430063)
摘要:
图像超分辨率(Super Resolution,SR)重建是计算机视觉领域中提高图像和视频分辨率的一种重要图像处理技术,针对基于深度学习的图像重建模型层次过多以及梯度传输困难导致训练时间长、重建图像视觉效果不理想的问题,本文提出了一种改进残差块和对抗损失的GAN(Generative Adversarial Networks)图像超分辨率重建模型.首先,在模型结构上,设计剔除多余批规范化操作的残差块并组合成生成模型,将深度卷积网络作为判别模型把控重建图像的训练方向,以减少模型的计算量;然后,在损失函数中,引入Earth-Mover距离设计对抗损失以缓解模型梯度消失的问题,采用L1距离作为重建图像与高分辨率图像相似程度的度量以指导模型权重更新来提高重建视觉效果.在DIV2K、Set5、Set14数据集上的实验结果表明:该模型剔除多余批规范化后的训练时间相比改进前模型减少约14%并有效提高图像的重建效果,结合Earth-Mover距离与L1距离的损失函数有效地缓解了梯度消失的问题.模型相较于双三次插值、SRCNN、VDSR、DSRN模型,提高了对低分辨率图像的超分辨率重建效率和视觉效果.
关键词:  超分辨率重建  生成对抗网络  深度学习  Earth-Mover距离  对抗损失
DOI:10.11918/j.issn.0367-6234.201812115
分类号:TP391
文献标识码:A
基金项目:
GAN image super-resolution reconstruction model with improved residual block and adversarial loss
ZHANG Yangyi,LIN Hong,GUAN Yuhua,LIU Chun
(College of Computer Science and Technology, Wuhan University of Technology, Wuhan 430063, China)
Abstract:
Image super-resolution (SR) reconstruction is an important image processing technology to improve the resolution of image and video in computer vision. Image reconstruction model based on deep learning has not been satisfactory due to the too many layers involved, the excessively long training time resulting from difficult gradient transmission, and the unsatisfactory reconstructed image. This paper proposes a generative adversarial networks (GAN) image SR reconstruction model with improved residual block and adversarial loss. Firstly, on the model structure, the residual blocks of the excess batch normalization were designed and combined into a generative model, and the deep convolution network was used as the discriminant model to control the training direction of the reconstructed image to reduce the model’s calculation amount. Then, in the loss function, the Earth-Mover distance was designed to alleviate model gradient disappearance. The L1 distance was used as the measure of the degree of similarity between the reconstructed image and the high-resolution image to guide the model weight update to improve the reconstructed visual effect. Experimental results from the DIV2K, Set5, and Set14 datasets demonstrate that compared with the model before improvement, the training time of the proposed model was reduced by about 14% and the image reconstruction effect was effectively improved. For the loss function combined with Earth-Mover distance and L1 distance, gradient disappearance was effectively alleviated. Therefore, the proposed model significantly improved the SR reconstruction efficiency and visual effect of low-resolution images compared with Bicubic, SRCNN, VDSR, and DSRN model.
Key words:  super-resolution construction  Generative Adversarial Networks (GAN)  deep learning  Earth-Mover distance  adversarial loss

友情链接LINKS