Salt-And-Pepper Noise Removal 벤치마크
Salt-And-Pepper Noise Removal on BSD300 Noise Level 30%
PSNR
- 2018-03-12 — Noise2Noise: PSNR 39.83
- 2019-08-18 — CNN (Median Layers): PSNR 40.9
- 2025-02-13 — RTF-Net: PSNR 44.56
| Rank | Model | PSNR | Paper | Code | Year |
|---|---|---|---|---|---|
| 1 | RTF-Net | 44.56 | Residual Transformer Fusion Network for Salt and Pepper Image Denoising | 2025 | |
| 2 | CNN (Median Layers) | 40.90 | Convolutional Neural Network with Median Layers for Denoising Salt-and-Pepper Contaminations | llmpass/medianDenoise | 2019 |
| 3 | Noise2Noise | 39.83 | Noise2Noise: Learning Image Restoration without Clean Data | NVlabs/noise2noise · joeylitalien/noise2noise-pytorch · shivamsaboo17/Deep-Restore-PyTorch · +18 | 2018 |
| 4 | RTF-Net | 44.56 | Residual Transformer Fusion Network for Salt and Pepper Image Denoising | 2025 | |
| 5 | CNN (Median Layers) | 40.90 | Convolutional Neural Network with Median Layers for Denoising Salt-and-Pepper Contaminations | llmpass/medianDenoise | 2019 |
| 6 | Noise2Noise | 39.83 | Noise2Noise: Learning Image Restoration without Clean Data | NVlabs/noise2noise · joeylitalien/noise2noise-pytorch · shivamsaboo17/Deep-Restore-PyTorch · +18 | 2018 |