Image Denoising on SIDD Google Pixel (test)
46.56PSNRPAP + HB
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| PAP + HBNoise Model Category=Real-noise-based, Backbone=U-shape net (SID), Synthesis method=pattern-aligned patch sampling with high-bit refinement2021.10 | 46.56 | 97.8 | |
| Pixel-wiseNoise Model Category=Real-noise-based, Backbone=U-shape net (SID)2021.10 | 46.52 | 97.7 | |
| Calibrated P-GNoise Model Category=Physics-based, Backbone=U-shape net (SID)2021.10 | 46.48 | 97.6 | |
| ELDNoise Model Category=Physics-based, Backbone=U-shape net (SID)2021.10 | 46.43 | 97.7 | |
| Camera-Aware GANNoise Model Category=DNN-based, Backbone=U-shape net (SID)2021.10 | 45.96 | 97.5 | |
| Noise FlowNoise Model Category=DNN-based, Backbone=U-shape net (SID)2021.10 | 45.15 | 96.2 | |
| Paired dataNoise Model Category=Real-noise-based, Backbone=U-shape net (SID)2021.10 | 44.58 | 95.5 | |
| In-Camera P-GNoise Model Category=Physics-based, Backbone=U-shape net (SID)2021.10 | 36.65 | 77.6 |