Grayscale Image Denoising On Bsd68 Sigma50
Métriques
PSNR
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | PSNR |
|---|---|
| neural-nearest-neighbors-networks | 26.39 |
| blind-universal-bayesian-image-denoising-with | 25.1 |
| index-network | 26.34 |
| fast-and-interpretable-nonlocal-neural | 26.47 |
| adversarial-distortion-learning-for-medical | 26.87 |
| learning-deep-cnn-denoiser-prior-for-image | 26.19 |
| cdlnet-robust-and-interpretable-denoising | 26.35 |
| multi-level-wavelet-cnn-for-image-restoration | 26.53 |
| non-local-recurrent-network-for-image | 26.47 |
| ffdnet-toward-a-fast-and-flexible-solution | 26.29 |
| real-image-denoising-with-feature-attention | 26.4 |
| residual-dense-network-for-image-restoration | 26.43 |
| kbnet-kernel-basis-network-for-image | 26.65 |
| swinia-self-supervised-blind-spot-image | 26.61 |
| deep-graph-convolutional-image-denoising | 26.38 |