Laser & Optoelectronics Progress, Volume. 59, Issue 2, 0210001(2022)

Super-Resolution Reconstruction of Light Field Images via Sparse Representation

Peng Ge* and Yaotang You
Author Affiliations
  • College of Physics and Optoelectronic, South China University of Technology, Guangzhou , Guangdong 510641, China
  • show less
    Figures & Tables(7)
    Feature extraction of high resolution images
    Reconstructed results of light-field image herbs obtained by different methods
    Reconstructed results of light-field image boxes obtained by different methods
    Reconstructed results of light-field image bedroom obtained by different methods
    • Table 1. PSNR reconstructed by different algorithms

      View table

      Table 1. PSNR reconstructed by different algorithms

      ImageBicubicMethod in Ref.[12Method in Ref.[13SRCNNProposed method
      Herbs31.532.332.733.133.4
      Boxes33.134.534.634.735.4
      Bedroom33.034.134.734.935.2
    • Table 2. RMSE reconstructed by different algorithms

      View table

      Table 2. RMSE reconstructed by different algorithms

      ImageBicubicMethod in Ref.[12Method in Ref.[13SRCNNProposed method
      Herbs5.554.934.784.704.63
      Boxes4.884.023.953.823.68
      Bedroom4.874.294.153.993.93
    • Table 3. Comparison of DT time and SR time of different algorithms

      View table

      Table 3. Comparison of DT time and SR time of different algorithms

      ImageMethod in Ref.[12Method in Ref.[13Proposed method
      DTSRDTSRDTSR
      Herbs1536290.2102528.351310.7
      Boxes14593100.5119530.148612.3
      Bedroom1512695.5136227.753910.6
    Tools

    Get Citation

    Copy Citation Text

    Peng Ge, Yaotang You. Super-Resolution Reconstruction of Light Field Images via Sparse Representation[J]. Laser & Optoelectronics Progress, 2022, 59(2): 0210001

    Download Citation

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

    Category: Image Processing

    Received: Jan. 21, 2021

    Accepted: Mar. 5, 2021

    Published Online: Dec. 23, 2021

    The Author Email: Peng Ge (scpge@scut.edu.cn)

    DOI:10.3788/LOP202259.0210001

    Topics