Table 3 A quantitative comparison of different models on the Dense-Haze, NH-Haze, and I-Haze datasets is conducted.

From: SAD-Net: a full spectral self-attention detail enhancement network for single image dehazing

Method

Dense-Haze

NH-Haze

I-Haze

PSNR

SSIM

PSNR

SSIM

PSNR

SSIM

base_all

15.80

0.51

18.87

0.65

16.89

0.68

base_a

16.60

0.55

19.72

0.67

19.67

0.80

base_c

16.20

0.51

18.94

0.64

19.76

0.71

SAD-Net

17.16

0.55

20.48

0.72

21.65

0.84

  1. We compare PSNR and SSIM, where higher values indicate better performance.
  2. The best result is highlighted in bold.
Back to article page