Research Article
DFAN: Dual Feature Aggregation Network for Lightweight Image Super-Resolution
Table 5
Quantitative results for
SR with the blur-down degradation model. Best results are highlighted.
| Model | Scale | Params (K) | MultAdds (G) | Set5 | Set14 | BSD100 | Urban100 | Manga109 | PSNR | SSIM | PSNR | SSIM | PSNR | SSIM | PSNR | SSIM | PSNR | SSIM |
| Bicubic | × 3 | — | — | | | | | | | | | | | SRCNN [4] | × 3 | | | | | | | | | | | | | FSRCNN [37] | × 3 | | | | | | | | | | | | | VDSR [5] | × 3 | | | | | | | | | | | | | IDN [12] | × 3 | | | | | | | | | | | | | IMDN [15] | × 3 | | | | | | | | | | | | | CARN [11] | × 3 | | | | | | | | | | | | | DFAN | × 3 | | | | | | | | | | | | |
|
|