Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Laser & Optoelectronics Progress, Volume. 56, Issue 23, 231010(2019)

Image Super-Resolution Reconstruction Method Using Dual Discriminator Based on Generative Adversarial Networks

Piaoyi Yuan** and Yaping Zhang*
Author Affiliations
  • School of Information Science and Technology, Yunnan Normal University, Kunming, Yunnan 650500, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (8)
    Equations (0)
    References (25)
    Cited By (4)
    Tools
    Paper Information
    Topics
    Figures & Tables(8)
    Generator model structure of DDSRRN

    Fig. 1. Generator model structure of DDSRRN

    Download full size
    Discriminator model structure of DDSRRN

    Fig. 2. Discriminator model structure of DDSRRN

    Download full size
    Visualized checkerboard artifact images of deconvolution upsampling structure

    Fig. 3. Visualized checkerboard artifact images of deconvolution upsampling structure

    Download full size
    Comparison of SPSN and SSIM between DDSRRN and SRGAN models on DIV2K validation set. (a) SPSN;(b) SSIM

    Fig. 4. Comparison of SPSN and SSIM between DDSRRN and SRGAN models on DIV2K validation set. (a) SPSN;(b) SSIM

    Download full size
    Comparison of ”0846” building reconstruction with magnification of 4 in DIV2K dataset

    Fig. 5. Comparison of ”0846” building reconstruction with magnification of 4 in DIV2K dataset

    Download full size
    Comparison of ”Baby” reconstruction in Set5 dataset

    Fig. 6. Comparison of ”Baby” reconstruction in Set5 dataset

    Download full size
    Comparison of “Butterfly” reconstruction with magnification of 4 in Set5 dataset

    Fig. 7. Comparison of “Butterfly” reconstruction with magnification of 4 in Set5 dataset

    Download full size

    • Table 1. Average performance of each model on baseline dataset and DIV2K validation set

      View table

      Table 1. Average performance of each model on baseline dataset and DIV2K validation set

      DatasetAmplificationfactorBicubicSRGANESPCNSRCNNEDSRRDNDDSRRN
      RPSNSSIMRPSNSSIMRPSNSSIMRPSNSSIMRPSNSSIMRPSNSSIMRPSNSSIM
      Set5Set14BSD100DIV2K444428.43 0.79826.01 0.70425.97 0.67026.66 0.74929.07 0.67128.02 0.64527.17 0.60128.64 0.62330.07 0.80928.65 0.71427.45 0.70627.78 0.79528.97 0.80527.49 0.75026.90 0.71027.78 0.77532.62 0.89728.80 0.78727.71 0.74229.38 0.90332.61 0.89928.81 0.78627.78 0.74329.97 0.80629.94 0.81428.97 0.75128.05 0.71330.04 0.799
    Tools

    Get Citation

    Copy Citation Text

    Piaoyi Yuan, Yaping Zhang. Image Super-Resolution Reconstruction Method Using Dual Discriminator Based on Generative Adversarial Networks[J]. Laser & Optoelectronics Progress, 2019, 56(23): 231010

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Set citation alerts for article
    Save article for my favorites
    Paper Information

    Category: Image Processing

    Received: May. 13, 2019

    Accepted: Jun. 3, 2019

    Published Online: Nov. 27, 2019

    The Author Email: Piaoyi Yuan (1970915834@qq.com), Yaping Zhang (zhangyp@ynnu.edu.cn)

    DOI:10.3788/LOP56.231010

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology