DnCNN (n2t)

Reported on 4 benchmarks across 2 tasks · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision2 results

DenoisingonHanzi
PSNR· 2019-01-30
13.9
best: 14.35 (SwinIA)
SOTA
Noise2Self: Blind Denoising by Self-Supervision arXiv:1901.11365
DenoisingonCellNet
PSNR· 2019-01-30
34.4
SOTA
Noise2Self: Blind Denoising by Self-Supervision arXiv:1901.11365

Adversarial2 results

3D ArchitectureonHanzi
PSNR· 2019-01-30
13.9
best: 14.35 (SwinIA)
SOTA
Noise2Self: Blind Denoising by Self-Supervision arXiv:1901.11365
3D ArchitectureonCellNet
PSNR· 2019-01-30
34.4
SOTA
Noise2Self: Blind Denoising by Self-Supervision arXiv:1901.11365