Color Image Denoising On Cbsd68 Sigma50
Métriques
PSNR
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | PSNR |
|---|---|
| memnet-a-persistent-memory-network-for-image | 26.33 |
| stimulating-the-diffusion-model-for-image | 28.69 |
| residual-conditioned-optimal-transport | 28.25 |
| beyond-deep-residual-learning-for-image | 28.01 |
| stimulating-the-diffusion-model-for-image | 26.63 |
| adversarial-distortion-learning-for-medical | 29.02 |
| blind-universal-bayesian-image-denoising-with | 26.60 |
| patch-craft-video-denoising-by-deep-modeling | 27.93 |
| learning-deep-cnn-denoiser-prior-for-image | 27.86 |
| videnn-deep-blind-video-denoising | 27.63 |
| real-image-denoising-with-feature-attention | 28.14 |
| akdt-adaptive-kernel-dilation-transformer-for | 28.68 |
| instruct-ipt-all-in-one-image-processing-1 | 28.61 |
| residual-dense-network-for-image-super | 28.34 |
| rethinking-the-csc-model-for-natural-images | 28.00 |
| pre-trained-image-processing-transformer | 29.39 |
| ffdnet-toward-a-fast-and-flexible-solution | 27.96 |
| stimulating-the-diffusion-model-for-image | 28.69 |