Optics and Precision Engineering, Volume. 32, Issue 12, 1954(2024)

Dual attention refinement single image desnowing

Mingzhu SHI1...2,*, Bin ZAO1,2, Yuhao SU1,2, Xinhui LIN1,2, Siqi KONG1,2, and Muxian TAN12 |Show fewer author(s)
Author Affiliations
  • 1College of Electronic and Communication Engineering, Tianjin Normal University, Tianjin300387, China
  • 2Tianjin Key Laboratory of Wireless Mobile Communications and Power Transmission, Tianjin Normal University, Tianjin300387, China
  • show less
    Figures & Tables(11)
    Structure of dual Attention refinement desnowing network
    Channel attention and pixel attention
    Gated-Dconv feed-forward (GDFN)
    Results of snow removal by different methods on the CSD dataset
    Visualization comparison of different snow removal methods for texture details
    Visual comparison with other methods on real snow images
    Results of ablation experiments of branch network and refinement processing module for snow removal
    • Table 1. Results of different desnowing algorithms on three datesets

      View table
      View in Article

      Table 1. Results of different desnowing algorithms on three datesets

      方法CSD(2 000)SRRS(2 000)Snow100K(2 000)#Param# GMacs
      PSNR/dBSSIMPSNR/dBSSIMPSNR/dBSSIM
      Zheng220.210.7919.120.8023.860.82--
      DesnowNet520.130.8120.380.8430.500.9415.6 M1.7 KG
      CycleGAN2120.980.8020.210.7426.810.897.84 M42.38 G
      RESCAN2222.110.8122.790.86----
      All in One2326.310.8724.980.8826.070.8844 M12.26 G
      JSTASR627.960.8825.820.8923.120.8665 M-
      HDCWNet729.060.9127.780.9231.540.956.99 M9.78 G
      TransWeather2431.760.9328.290.9231.820.9321.9 M5.64 G
      Ours32.160.9630.080.9532.030.955.48 M6.12 G
    • Table 2. Comparison results of different construction strategies

      View table
      View in Article

      Table 2. Comparison results of different construction strategies

      指标PSNR/dBSSIM
      分支网络串联结构29.830.94
      维度不拆分并行化策略31.940.95
      维度拆分并行化策略32.160.96
    • Table 3. Comparison results of different attention strategies

      View table
      View in Article

      Table 3. Comparison results of different attention strategies

      指标像素注意力空间注意力通道注意力
      PSNR/dB32.0531.9432.16
      SSIM0.960.960.96
    • Table 4. Results of ablation experiments on branching networks and refinement of processing modules

      View table
      View in Article

      Table 4. Results of ablation experiments on branching networks and refinement of processing modules

      纹理提取分支

      精细化

      处理模块

      U型特征提取分支网络

      指标

      (PSNR/SSIM)

      ××30.860.94
      ×31.430.95
      ×31.870.95
      32.160.96
    Tools

    Get Citation

    Copy Citation Text

    Mingzhu SHI, Bin ZAO, Yuhao SU, Xinhui LIN, Siqi KONG, Muxian TAN. Dual attention refinement single image desnowing[J]. Optics and Precision Engineering, 2024, 32(12): 1954

    Download Citation

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

    Category:

    Received: Nov. 13, 2023

    Accepted: --

    Published Online: Aug. 28, 2024

    The Author Email: SHI Mingzhu (shimz@tjnu.edu.cn)

    DOI:10.37188/OPE.20243212.1954

    Topics