Laser & Optoelectronics Progress, Volume. 59, Issue 2, 0209001(2022)

Multiscale Digital Hologram Reconstruction Based on Deep Learning

Jian Pu, Jinbin Gui*, and Kai Zhang
Author Affiliations
  • Faculty of Science, Kunming University of Science and Technology, Kunming , Yunnan 650550, China
  • show less
    Figures & Tables(8)
    Schematic of holographic wavefront recording
    Schematic of digital holographic reconstruction
    Improved U-Net structure, the size of the current feature map is located at the left of the rectangular box
    HS-Block structure
    Network structure for reconstructing multi-scale digital holograms
    Mixing digital holograms with different scales as a data set training deep learning model to compare the reconstruction effect of different resolution digital holograms
    Comparison of reconstruction results of different scale digital holograms by a single deep learning model
    • Table 1. Average PSNR and SSIM of test set

      View table

      Table 1. Average PSNR and SSIM of test set

      Parameter256×256512×512640×480
      AmplitudePhaseAmplitudePhaseAmplitudePhase
      PSNR /dB32.470825.416745.837628.313041.465137.7251
      SSIM0.96890.86850.99810.87480.99530.9131
    Tools

    Get Citation

    Copy Citation Text

    Jian Pu, Jinbin Gui, Kai Zhang. Multiscale Digital Hologram Reconstruction Based on Deep Learning[J]. Laser & Optoelectronics Progress, 2022, 59(2): 0209001

    Download Citation

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

    Category: Holography

    Received: Mar. 2, 2021

    Accepted: Mar. 10, 2021

    Published Online: Dec. 23, 2021

    The Author Email: Jinbin Gui (jinbingui@163.com)

    DOI:10.3788/LOP202259.0209001

    Topics