Gaussian Grayscale Image Denoising on Urban100
34.22PSNR (sigma=15)GRL-B+Ours-c
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| GRL-B+Ours-cTraining protocol=Separate model per noise level, Pre-trained CLIP model=true2024.03 | 34.22 | 31.95 | 28.74 | |
| GRL-BTraining protocol=Separate model per noise level2024.03 | 34.09 | 31.8 | 28.59 | |
| Restormer+Ours-cTraining protocol=Separate model per noise level, Pre-trained CLIP model=true2024.03 | 33.97 | 31.73 | 28.58 | |
| Restormer+Ours-cTraining protocol=Single model for all noise levels, Pre-trained CLIP model=true2024.03 | 33.96 | 31.67 | 28.58 | |
| RestormerTraining protocol=Separate model per noise level2024.03 | 33.79 | 31.46 | 28.29 | |
| RestormerTraining protocol=Single model for all noise levels2024.03 | 33.67 | 31.39 | 28.33 | |
| DRUNet+Ours-cTraining protocol=Single model for all noise levels, Pre-trained CLIP model=true2024.03 | 33.65 | 31.34 | 28.16 | |
| DRUNetTraining protocol=Single model for all noise levels2024.03 | 33.44 | 31.11 | 27.96 |