Journal of Applied Optics, Volume. 44, Issue 6, 1343(2023)

Image super-resolution reconstruction based on multi-scale two-stage network

Qingjiang CHEN... Lexuan YIN* and Luoyi SHAO |Show fewer author(s)
Author Affiliations
  • School of Science, Xi'an University of Architecture and Technology, Xi'an 710055, China
  • show less
    Figures & Tables(16)
    Network process
    Multiscale convolution layer
    Overall network structure
    Residual combination block
    Depth feature extraction block
    Shuffle unit
    Feature refinement module(FRM)
    Loss function curve under double magnification factor
    Comparison of training time for different algorithms
    Visual effect pictures of different algorithms when magnification factor is 2
    Comparison effect of different algorithms on dataset RealSR
    Failure cases on dataset RealSR
    Visual renderings of different loss functions
    • Table 1. Comparison of PSNR and SSIM values of different algorithms

      View table
      View in Article

      Table 1. Comparison of PSNR and SSIM values of different algorithms

      算法尺寸时间/sSet5Set14Urban100BSDS100Manga109
      PSNR/SSIMPSNR/SSIMPSNR/SSIMPSNR/SSIMPSNR/SSIM
      Bicubic2-33.66/0.929930.24/0.868826.88/0.840331.27/0.837730.30/0.9339
      SRCNN20.1836.66/0.952432.42/0.906329.50/0.894631.38/0.857035.74/0.9661
      FSRCNN20.0737.00/0.956032.63/0.908929.87/0.902032.83/0.900036.65/0.9709
      ESPCN20.0537.04/0.953033.40/0.915030.79/0.903733.55/0.905935.48/0.9666
      VDSR20.1337.53/0.958733.03/0.912430.76/0.914033.56/0.903137.22/0.9729
      SRResnet20.1237.58/0.954233.71/0.916532.07/0.895833.86/0.909535.73/0.9590
      本文算法20.1239.09/0.965834.53/0.925532.71/0.924134.52/0.920937.68/0.9727
      Bicubic3-30.39/0.868227.55/0.774224.46/0.734927.80/0.763526.95/0.8556
      SRCNN30.1832.75/0.909029.28/0.820926.24/0.798929.07/0.770230.59/0.9107
      FSRCNN30.0333.16/0.913929.43/0.824226.43/0.808029.11/0.753831.10/0.9210
      ESPCN30.0233.13/0.915629.49/0.845128.08/0.808030.91/0.827430.54/0.8949
      VDSR30.1333.66/0.921329.77/0.831427.14/0.827930.79/0.820432.01/0.9310
      SRResnet30.1233.91/0.918030.70/0.846528.24/0.810331.06/0.830030.88/0.8964
      本文算法30.1135.20/0.932231.50/0.864329.21/0.870031.65/0.879232.73/0.9429
      Bicubic4-28.42/0.810426.00/0.702723.14/0.655726.50/0.700324.89/0.7866
      SRCNN40.1830.48/0.862827.50/0.751324.52/0.722127.60/0.712027.58/0.8555
      FSRCNN40.0230.71/0.866027.59/0.754924.62/0.728028.36/0.722327.90/0.8610
      ESPCN40.0130.90/0.830627.73/0.762726.06/0.713228.92/0.744227.32/0.8153
      VDSR40.1231.25/0.833028.02/0.768025.18/0.754029.09/0.755828.83/0.8770
      SRResnet40.1132.05/0.901928.49/0.818426.75/0.746229.60/0.774328.48/0.8411
      本文算法40.1032.75/0.900129.66/0.815427.44/0.789429.94/0.795229.86/0.8846
    • Table 2. PSNR and SSIM values of different loss functions on Set5

      View table
      View in Article

      Table 2. PSNR and SSIM values of different loss functions on Set5

      参数L2α=0.01α=0.1α=0.4α=0.5α=0.6
      PSNR39.0638.8938.9238.8839.0938.85
      SSIM0.96470.96010.96200.96450.96580.9640
    • Table 3. PSNR and SSIM values on Set5 h

      View table
      View in Article

      Table 3. PSNR and SSIM values on Set5 h

      参数MSTSRNMSTSRN-RCBMSTSRN-DFEBMSTSRN-FRM
      PSNR39.0938.6739.0038.84
      SSIM0.96580.96140.95530.9629
      时间/s34.2036.6721.6631.33
    Tools

    Get Citation

    Copy Citation Text

    Qingjiang CHEN, Lexuan YIN, Luoyi SHAO. Image super-resolution reconstruction based on multi-scale two-stage network[J]. Journal of Applied Optics, 2023, 44(6): 1343

    Download Citation

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

    Category: Research Articles

    Received: Jan. 16, 2023

    Accepted: --

    Published Online: Mar. 12, 2024

    The Author Email: YIN Lexuan (尹乐璇)

    DOI:10.5768/JAO202344.0602004

    Topics