Table 2 Comparison of quantitative indicators (Model Size and Params) with several classical methods. The best results are marked in bold.
From: SVTSR: image super-resolution using scattering vision transformer
Method | Scale | Model Size(MB) | Params(M) |
|---|---|---|---|
RCAN | \(\times 2\) | 119.12 | 15.4 |
SwinIR | \(\times 2\) | 112.56 | 11.8 |
HAT | \(\times 2\) | 161.27 | 20.6 |
SVTSR(ours) | \(\times 2\) | 21.16 | 2.3 |
RCAN | \(\times 3\) | 120.11 | 15.5 |
SwinIR | \(\times 3\) | 113.97 | 11.9 |
HAT | \(\times 3\) | 162.28 | 20.8 |
SVTSR(ours) | \(\times 3\) | 22.56 | 2.5 |
RCAN | \(\times 4\) | 120.25 | 15.6 |
SwinIR | \(\times 4\) | 113.69 | 11.9 |
HAT | \(\times 4\) | 162.40 | 20.77 |
SVTSR(ours) | \(\times 4\) | 22.28 | 2.5 |
