Image Generation on CIFAR-10 Poisson noise 10% clean 90% noisy (train)
14.7FIDSCoRe
Evaluation results
| Method | Links | |
|---|---|---|
| SCoRef_cutoff=0.30, t'=722026.04 | 14.7 | |
| SCoRef_cutoff=0.20, t'=1192026.04 | 14.9 | |
| SCoRef_cutoff=0.40, t'=582026.04 | 24.2 | |
| Diffusion ModelPost-processing=Noise2Void (N2V)2026.04 | 31.6 | |
| NR-GAN2026.04 | 46.5 | |
| Diffusion ModelPost-processing=Bilateral filter2026.04 | 68 | |
| SDEdit2026.04 | 151.3 | |
| Diffusion Model2026.04 | 168.7 |