Skip to main content

Table 4 Quantitative comparisons on cremi_triplet and mouse_triplet

From: Sparse self-attention aggregation networks for neural sequence slice interpolation

Methods

cremi_triplet A

cremi_triplet B

cremi_triplet C

mouse_triplet

 

PSNR

SSIM

PSNR

SSIM

PSNR

SSIM

IE

PSNR

SSIM

IE

SepConv-L s [9]

17.52

0.4095

16.32

0.3522

16.07

0.3454

29.82

12.56

0.1573

48.03

DAIN-L s [12]

16.78

0.4264

15.67

0.3460

15.24

0.3210

33.59

13.06

0.1973

44.26

SSAN(Ours)

18.26

0.4374

16.79

0.3712

16.46

0.3575

28.38

15.04

0.2156

34.81

  1. The proposed SSAN algorithm significantly surpasses other methods in terms of PSNR, SSIM and IE