Table 4.
PSNR and SSIM metrics of the denoising methods tested on the SIPI data set. For each σ value (i.e. the intensity of the speckle noise), we report the average metric computed on the 44 images of the data set
| Metric | PSNR | SSIM | ||||||
|---|---|---|---|---|---|---|---|---|
| Method ∣ σ | 0.05 | 0.1 | 0.2 | 0.3 | 0.05 | 0.1 | 0.2 | 0.3 |
| WNNM | 25.57 | 24.68 | 23.35 | 22.32 | 0.681 | 0.659 | 0.630 | 0.602 |
| SAR-BM3D | 27.36 | 26.01 | 24.71 | 23.65 | 0.730 | 0.699 | 0.673 | 0.651 |
| PCA-BM3D | 25.09 | 24.36 | 23.05 | 22.10 | 0.652 | 0.640 | 0.614 | 0.585 |
| NCSR | 26.60 | 25.36 | 23.61 | 22.36 | 0.665 | 0.669 | 0.619 | 0.588 |
| BM3D-CNN | 26.85 | 24.20 | 20.21 | 17.26 | 0.733 | 0.569 | 0.31 | 0.215 |