TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/SG-ShadowNet (ECCV 2022) (256x256)

SG-ShadowNet (ECCV 2022) (256x256)

Reported on 24 benchmarks across 3 tasks

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision16 results

  • Image EditingonSRD
    LPIPS
    0.443
    best: 0.219 (HomoFormer (CVPR 2024) (512x512))
  • Image EditingonSRD
    PSNR
    24.1
    best: 26.47 (DC-ShadowNet (ICCV 2021) (512x512))
  • Image EditingonSRD
    RMSE
    4.6
    best: 3.37 (RASM)
  • Image EditingonSRD
    SSIM
    0.636
    best: 0.827 (HomoFormer (CVPR 2024) (512x512))
  • Image EditingonISTD+
    LPIPS
    0.369
    best: 0.183 (SP+M-Net (ICCV 2019) (512x512))
  • Image EditingonISTD+
    PSNR
    26.8
    best: 28.53 (HomoFormer (CVPR 2024) (512x512))
  • Image EditingonISTD+
    RMSE
    3.32
    best: 2.53 (RASM)
  • Image EditingonISTD+
    SSIM
    0.717
    best: 0.866 (SP+M-Net (ICCV 2019) (512x512))
  • Shadow RemovalonSRD
    LPIPS
    0.443
    best: 0.219 (HomoFormer (CVPR 2024) (512x512))
  • Shadow RemovalonSRD
    PSNR
    24.1
    best: 26.47 (DC-ShadowNet (ICCV 2021) (512x512))
  • Shadow RemovalonSRD
    RMSE
    4.6
    best: 3.37 (RASM)
  • Shadow RemovalonSRD
    SSIM
    0.636
    best: 0.827 (HomoFormer (CVPR 2024) (512x512))
  • Shadow RemovalonISTD+
    LPIPS
    0.369
    best: 0.183 (SP+M-Net (ICCV 2019) (512x512))
  • Shadow RemovalonISTD+
    PSNR
    26.8
    best: 28.53 (HomoFormer (CVPR 2024) (512x512))
  • Shadow RemovalonISTD+
    RMSE
    3.32
    best: 2.53 (RASM)
  • Shadow RemovalonISTD+
    SSIM
    0.717
    best: 0.866 (SP+M-Net (ICCV 2019) (512x512))

Methodology8 results

  • 16konSRD
    LPIPS
    0.443
    best: 0.219 (HomoFormer (CVPR 2024) (512x512))
  • 16konSRD
    PSNR
    24.1
    best: 26.47 (DC-ShadowNet (ICCV 2021) (512x512))
  • 16konSRD
    RMSE
    4.6
    best: 3.37 (RASM)
  • 16konSRD
    SSIM
    0.636
    best: 0.827 (HomoFormer (CVPR 2024) (512x512))
  • 16konISTD+
    LPIPS
    0.369
    best: 0.183 (SP+M-Net (ICCV 2019) (512x512))
  • 16konISTD+
    PSNR
    26.8
    best: 28.53 (HomoFormer (CVPR 2024) (512x512))
  • 16konISTD+
    RMSE
    3.32
    best: 2.53 (RASM)
  • 16konISTD+
    SSIM
    0.717
    best: 0.866 (SP+M-Net (ICCV 2019) (512x512))