Image Denoising on Set14 Gaussian σ=25 (test)
31.4PSNRNoise2Clean
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Noise2CleanSupervision=Supervised, train_passes=1, test_passes=12023.05 | 31.4 | 0.869 | |
| Noise2NoiseSupervision=Supervised, train_passes=1, test_passes=12023.05 | 31.37 | 0.868 | |
| Laine19-pmeSupervision=Self-supervised, train_passes=4, test_passes=4, assumed_known_noise_model=true2023.05 | 31.36 | 0.866 | |
| R2RSupervision=Self-supervised, train_passes=1, test_passes=502023.05 | 31.32 | 0.865 | |
| DCD-NetSupervision=Self-supervised, train_passes=3, test_passes=12023.05 | 31.29 | 0.862 | |
| B2UBSupervision=Self-supervised, train_passes=17, test_passes=12023.05 | 31.27 | 0.864 | |
| Honzatko-pmeSupervision=Self-supervised, train_passes=1, test_passes=1, assumed_known_noise_model=true2023.05 | 31.25 | — | |
| NBR2NBRSupervision=Self-supervised, train_passes=2, test_passes=12023.05 | 31.09 | 0.864 | |
| CBM3DSupervision=Traditional2023.05 | 30.88 | 0.854 | |
| DBSNSupervision=Self-supervised, train_passes=2, test_passes=12023.05 | 30.63 | 0.846 | |
| SwinIASupervision=Self-supervised (True BSN), train_passes=1, test_passes=1, self_implemented=true2023.05 | 30.56 | 0.856 | |
| Self2SelfSupervision=Self-supervised, train_passes=1, test_passes=502023.05 | 30.08 | 0.839 | |
| Laine19Supervision=Self-supervised (True BSN), train_passes=4, test_passes=42023.05 | 29.93 | 0.83 | |
| Noisier2NoiseSupervision=Self-supervised, train_passes=1, test_passes=1, assumed_known_noise_model=true2023.05 | 29.64 | 0.832 | |
| Noise2SameSupervision=Self-supervised, train_passes=2, test_passes=1, self_implemented=true2023.05 | 29.53 | 0.827 | |
| Noise2VoidSupervision=Self-supervised, train_passes=1, test_passes=12023.05 | 28.84 | 0.802 |