Figure 1.
Composition of double regression model
Figure 2.
Super resolution reconstruction process
Figure 3.
Recursive learning
TABLE I.
Comparison of the results of PSNR reconstruction by two times of each algorithm
| Datasets | FSRCNN | SRGAN | ESRGAN | Ours |
|---|---|---|---|---|
| Set5 | 32.40 | 33.19 | 33.46 | 34.68 |
| Set14 | 29.52 | 29.56 | 29.47 | 30.56 |
| Bsd100 | 26.74 | 29.47 | 29.78 | 29.78 |
TABLE II.
Comparison of SSIM results of four times reconstruction of each algorithm
| Datasets | FSRCNN | SRGAN | ESRGAN | Ours |
|---|---|---|---|---|
| Set5 | 0.8657 | 0.8657 | 0.8569 | 0.6895 |
| Set14 | 0.7564 | 0.7369 | 0.8697 | 0.7698 |
| Bsd100 | 0.7156 | 0.6689 | 0.6783 | 0.6856 |
Figure 4.
Double magnification reconstruction comparison of each algorithm
Figure 5.
Comparison of four times magnification reconstruction of each algorithm