Table 3 Comparison of our model’s denoising performance with a few benchmark models at different datasets such as CBSD68, KODAK24, and McMaster.

From: Enhancing U-Net for image denoising with bilateral filter noise residue and gradient estimation (BIRUNet)

 

KODAK24

McMaster

CBSD68

σ

15

25

50

15

25

50

15

25

50

CBM3D12

34.28

31.68

28.46

34.06

31.66

28.51

33.50

30.69

27.37

DnCNN6

34.48

32.03

28.85

33.44

31.51

28.61

33.89

31.33

27.97

FFDNet9

34.63

32.13

28.98

34.66

32.35

29.18

33.87

31.21

27.96

ADNet35

34.76

32.26

29.10

34.93

32.56

29.36

33.99

31.31

28.04

GradNet37

34.85

32.35

29.23

34.81

32.45

29.39

34.07

31.39

28.12

BIRUNet

33.96

32.39

29.26

33.49

32.62

29.42

32.91

31.44

28.24

Back to article page