Table 6 Quantitative comparison on benchmark datasets for scale factor \(\times \)4.

From: Lightweight interactive feature inference network for single-image super-resolution

Type

Model

Params

Multi-Adds

Set5

Set14

B100

Urban100

Manga109

PSNR(dB)/SSIM

PSNR(dB)/SSIM

PSNR(dB)/SSIM

PSNR(dB)/SSIM

PSNR(dB)/SSIM

CNN-based

SRCNN1

57K

52.7G

30.48/0.8628

27.49/0.7503

26.90/0.7101

24.52/0.7221

27.66/0.8505

FSRCNN38

12K

4.6G

30.71/0.8657

27.59/0.7535

26.98/0.7150

24.62/0.7280

27.90/0.8517

VDSR15

665K

612.6G

31.35/0.8838

28.01/0.7674

27.29/0.7251

25.18/0.7524

28.83/0.8809

DRCN5

1774K

17974G

31.53/0.8854

28.02/0.7670

27.23/0.7233

25.14/0.7510

28.98/0.8816

LapSRN39

813K

149.4G

31.54/0.8850

28.19/0.7720

27.32/0.7280

25.21/0.7560

29.09/0.8845

DRRN40

297K

6797G

31.68/0.8888

28.21/0.7720

27.38/0.7284

25.44/0.7638

29.46/0.8960

MemNet20

677K

2662.4G

31.74/0.8893

28.26/0.7723

27.40/0.7281

25.50/0.7630

-

CARN6

1592K

90.9G

32.13/0.8937

28.60/0.7806

27.58/0.7349

26.07/0.7837

-

CBPN41

1197K

97.9G

32.21/0.8944

28.63/0.7813

27.58/0.7356

26.14/0.7869

-

AWSRN-M42

1254K

72.0G

32.21/0.8954

28.65/0.7832

27.60/0.7368

26.15/0.7884

30.56/0.9093

OISR-RK2-s43

1520 K

114.2 G

32.21/0.8950

28.63/0.7822

27.58/0.7364

26.14/0.7874

-

A2F-S9

331k

18.6G

31.87/0.8900

28.36/0.7760

27.41/0.7305

25.58/0.7685

29.77/0.8987

LESRCNN44

516K

28.6G

31.88/0.8903

28.44/0.7772

27.45/0.7313

25.77/0.7732

-

WMRN48

536K

45.7G

32.00/0.8925

28.47/0.7786

27.49/0.7328

25.89/0.7789

30.11/0.9040

LMAN-s49

672K

65.5G

32.12/0.8939

28.53/0.7798

27.51/0.7340

25.96/0.7813

30.30/0.9062

MSWSR51

1228 K

101.7G

32.01/0.8914

28.47/0.7776

27.48/0.7311

25.78/0.7744

30.01/0.8999

Cross-SRN52

1296K

74.2G

32.24/0.8954

28.59/0.7817

27.58/0.7364

26.16/0.7881

30.53/0.9081

ACNet29

1784K

347.9G

31.83/0.8903

28.46/0.7788

27.48/0.7326

25.93/0.7798

-

CRMBN53

495K

-

32.07/0.8923

28.50/0.7783

27.50/0.7327

25.83/0.7771

-

FMEN54

769K

44.2G

32.24/0.8955

28.70/0.7839

27.63/0.7379

26.28/0.7908

30.70/0.9107

AFAN55

1226K

90.1G

32.30/0.8951

28.66/0.7838

27.61/0.7383

26.27/0.7913

30.63/0.9109

CFGN58

621K

33.9G

32.32/0.8957

28.67/0.7832

27.60/0.7377

26.22/0.7916

30.63/0.9101

Tranformered-based

DRSAN-48m8

1271K

88.7G

32.34/0.8960

28.65/0.7841

27.63/0.7390

26.33/0.7936

-

ESRT56

751K

67.7G

32.19/0.8947

28.69/0.7833

27.69/0.7379

26.39/0.7962

30.75/0.9100

LBNet57

742K

38.9G

32.29/0.8960

28.68/0.7832

27.62/0.7382

26.27/0.7906

30.76/0.9111

Ngswin59

1019K

36.4G

32.33/0.8963

28.78/0.7859

27.66/0.7396

26.45/0.7963

30.80/0.9128

IFIN-S(ours)

470K

31.6G

32.27/0.8958

28.68/0.7834

27.62/0.7381

26.17/0.7890

30.64/0.9106

IFIN(ours)

991K

64.6G

32.47/0.8988

28.80/0.7871

27.70/0.7414

26.64/0.7979

31.06/0.9156

Back to article page