CBDNet (Blind)

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

DenoisingonDarmstadt Noise Dataset
PSNR (sRGB)· 2018-07-12
38.06
best: 40.35 (Image Unprocessing)
SOTA
Toward Convolutional Blind Denoising of Real Photographs arXiv:1807.04686
DenoisingonDarmstadt Noise Dataset
SSIM (sRGB)· 2018-07-12
0.9421
best: 0.9641 (Image Unprocessing)
SOTA
Toward Convolutional Blind Denoising of Real Photographs arXiv:1807.04686

Adversarial2 results

3D ArchitectureonDarmstadt Noise Dataset
PSNR (sRGB)· 2018-07-12
38.06
best: 40.35 (Image Unprocessing)
SOTA
Toward Convolutional Blind Denoising of Real Photographs arXiv:1807.04686
3D ArchitectureonDarmstadt Noise Dataset
SSIM (sRGB)· 2018-07-12
0.9421
best: 0.9641 (Image Unprocessing)
SOTA
Toward Convolutional Blind Denoising of Real Photographs arXiv:1807.04686