Image Super Resolution On Ffhq 256 X 256 4X
Metriken
FID
MS-SSIM
PSNR
SSIM
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | FID | MS-SSIM | PSNR | SSIM |
|---|---|---|---|---|
| accelerating-the-super-resolution | 139.78 | 0.930 | 22.45 | 0.709 |
| component-attention-guided-face-super | 74.43 | 0.958 | 27.42 | 0.816 |
| binary-diffusion-probabilistic-model | 5.71 | - | 30.05 | 0.864 |
| feedback-network-for-image-super-resolution | 132.59 | 0.895 | 21.96 | 0.693 |
| bayesian-image-reconstruction-using-deep | - | - | 24.16 | 0.70 |
| pulse-self-supervised-photo-upsampling-via | - | - | 15.74 | 0.37 |
| enhancenet-single-image-super-resolution | 116.38 | 0.897 | 23.64 | 0.701 |
| photo-realistic-single-image-super-resolution | 156.07 | 0.757 | 17.57 | 0.415 |
| hifacegan-face-renovation-via-collaborative | 5.36 | 0.971 | 28.65 | 0.816 |
| image-super-resolution-using-deep | 147.21 | 0.900 | 23.12 | 0.688 |
| esrgan-enhanced-super-resolution-generative | 166.36 | 0.747 | 15.43 | 0.267 |
| enhanced-deep-residual-networks-for-single | 129.14 | 0.901 | 22.47 | 0.706 |