Table 8 Comparison of ESDAN and other SOTA methods on the OASIS dataset. The best and second-best metrics are marked in red and blue, respectively.

From: A general lightweight image super-resolution with sharpening enhancement and double attention network

Models

Scale

Params(K)

PSNR (dB)

SSIM

Bicubic

×4

-

29.88

0.8574

EDSR46

44,113

32.55

0.9184

RDN54

5898

32.57

0.9241

RCAN47

42,332

32.81

0.9224

SwinIR13

11,745

33.24

0.9287

RDST-E48

2406

33.26

0.9291

ESDAN (Ours)

554

33.25

0.9310

Back to article page