Image Denoising on Set14 Poisson λ∈[5, 50] (test)
30.1PSNRB2UB
Evaluation results
| Method | Links | ||
|---|---|---|---|
| B2UBSupervision=Self-supervised, train_passes=17, test_passes=12023.05 | 30.1 | 0.844 | |
| Noise2CleanSupervision=Supervised, train_passes=1, test_passes=12023.05 | 30.02 | 0.842 | |
| Noise2NoiseSupervision=Supervised, train_passes=1, test_passes=12023.05 | 30.02 | 0.842 | |
| DCD-NetSupervision=Self-supervised, train_passes=3, test_passes=12023.05 | 29.99 | 0.843 | |
| NBR2NBRSupervision=Self-supervised, train_passes=2, test_passes=12023.05 | 29.79 | 0.838 | |
| SwinIASupervision=Self-supervised (True BSN), train_passes=1, test_passes=1, self_implemented=true2023.05 | 29.35 | 0.827 | |
| Laine19Supervision=Self-supervised (True BSN), train_passes=4, test_passes=42023.05 | 28.94 | 0.808 | |
| Self2SelfSupervision=Self-supervised, train_passes=1, test_passes=502023.05 | 28.83 | 0.841 | |
| R2RSupervision=Self-supervised, train_passes=1, test_passes=502023.05 | 28.77 | 0.765 | |
| DBSNSupervision=Self-supervised, train_passes=2, test_passes=12023.05 | 28.72 | 0.8 | |
| Laine19-pmeSupervision=Self-supervised, train_passes=4, test_passes=4, assumed_known_noise_model=true2023.05 | 28.65 | 0.785 | |
| AnscombeSupervision=Traditional2023.05 | 28.51 | 0.817 | |
| Noise2VoidSupervision=Self-supervised, train_passes=1, test_passes=12023.05 | 27.43 | 0.745 | |
| Noise2SameSupervision=Self-supervised, train_passes=2, test_passes=1, self_implemented=true2023.05 | 26.37 | 0.721 |