Optical Instruments, Volume. 46, Issue 5, 65(2024)

Low light image enhancement based on semantic information and attention mechanism

Haobin LI and Yunsong HUA*
Author Affiliations
  • School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China
  • show less
    Figures & Tables(10)
    Flow chart of the proposed model
    Joint training U-Net structure
    Structure of the attention mechanism
    Semantic segmentation results
    Low light enhancement results from different methods in LISU datasets
    Comparison of the visualization results with and without semantic informations
    Comparison of the attention map visualization with and without semantic informations
    Comparison of the visualization results with and without attention mechanism module
    • Table 1. Comparison of indices of the different methods

      View table
      View in Article

      Table 1. Comparison of indices of the different methods

      指标EnlightenGANRetinexNetKinDMBLLENZero-DCE本文方法
      PSNR12.5414.3114.0715.3515.8118.52
      SSIM0.440.470.560.620.460.72
    • Table 2. Impact of deleting different modules on index

      View table
      View in Article

      Table 2. Impact of deleting different modules on index

      指标删除注意力机制模块删除语义信息输入本文方法
      PSNR17.0417.4718.52
      SSIM0.550.680.72
    Tools

    Get Citation

    Copy Citation Text

    Haobin LI, Yunsong HUA. Low light image enhancement based on semantic information and attention mechanism[J]. Optical Instruments, 2024, 46(5): 65

    Download Citation

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

    Category:

    Received: Jul. 23, 2023

    Accepted: --

    Published Online: Jan. 3, 2025

    The Author Email: HUA Yunsong (hyuns_yz@163.com)

    DOI:10.3969/j.issn.1005-5630.202307230106

    Topics