Image Denoising on SIDD iPhone 7 (test)
56.79PSNRPAP + 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 | 56.79 | 0.996 | |
| Pixel-wiseNoise Model Category=Real-noise-based, Backbone=U-shape net (SID)2021.10 | 56.76 | 0.996 | |
| ELDNoise Model Category=Physics-based, Backbone=U-shape net (SID)2021.10 | 56.73 | 0.996 | |
| Calibrated P-GNoise Model Category=Physics-based, Backbone=U-shape net (SID)2021.10 | 56.71 | 0.996 | |
| Paired dataNoise Model Category=Real-noise-based, Backbone=U-shape net (SID)2021.10 | 55.64 | 0.995 | |
| Camera-Aware GANNoise Model Category=DNN-based, Backbone=U-shape net (SID)2021.10 | 55.48 | 0.994 | |
| Noise FlowNoise Model Category=DNN-based, Backbone=U-shape net (SID)2021.10 | 48.29 | 0.983 | |
| In-Camera P-GNoise Model Category=Physics-based, Backbone=U-shape net (SID)2021.10 | 44.58 | 0.96 |