Image Super Resolution On Ffhq 512 X 512 4X
评估指标
FED
FID
LLE
LPIPS
MS-SSIM
NIQE
PSNR
SSIM
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | FED | FID | LLE | LPIPS | MS-SSIM | NIQE | PSNR | SSIM |
|---|---|---|---|---|---|---|---|---|
| wavelet-srnet-a-wavelet-based-cnn-for-multi | 0.0964 | 16.472 | 2.702 | 0.2443 | 0.952 | 12.217 | 28.750 | 0.806 |
| 模型 2 | - | - | - | - | 0.976 | - | 30.465 | 0.859 |
| feedback-network-for-image-super-resolution | 0.0984 | 20.032 | 2.066 | 0.2406 | 0.953 | 13.901 | 29.577 | 0.827 |
| super-fan-integrated-facial-landmark | 0.1416 | 14.811 | 2.333 | 0.2357 | 0.913 | 8.719 | 25.463 | 0.729 |
| hifacegan-face-renovation-via-collaborative | 0.0716 | 1.898 | 2.071 | 0.0723 | 0.971 | 6.961 | 30.824 | 0.838 |
| photo-realistic-single-image-super-resolution | 0.1097 | 4.396 | 2.269 | 0.1313 | 0.935 | 7.378 | 27.494 | 0.735 |
| esrgan-enhanced-super-resolution-generative | 0.1107 | 3.503 | 2.261 | 0.1221 | 0.935 | 6.984 | 27.134 | 0.741 |
| enhanced-deep-residual-networks-for-single | 0.0843 | 20.605 | 2.003 | 0.2475 | 0.961 | 13.636 | 30.188 | 0.824 |