List your company
ResearchFormerly WizWand

Gaussian Image Denoising on McMaster 2011 (test)

30.5PSNR (sigma=50)DMID-d
28.430428.967729.50530.0423Jul 8, 2023Aug 10, 2023Sep 13, 2023Oct 17, 2023Nov 19, 2023Dec 23, 2023Jan 26, 2024
Updated 8mo ago

Evaluation results

MethodLinks
DMID-dTraining strategy=Noise-blind (various noise levels)2023.0730.535.7233.49
ART*MACs (G)=4220, Inf. (ms)=OOM, Image Size=512 x 512 x 32024.0130.3135.6833.41
RestormerMACs (G)=564, Inf. (ms)=350, Image Size=512 x 512 x 32024.0130.335.6133.34
RestormerTraining strategy=Noise-specific (separate models)2023.0730.335.6133.34
RestormerTraining strategy=Noise-blind (various noise levels)2023.0730.2935.5533.31
SwinIRMACs (G)=2991, Inf. (ms)=1850, Image Size=512 x 512 x 32024.0130.2235.6133.2
CGNetMACs (G)=444, Inf. (ms)=215, Image Size=512 x 512 x 32024.0130.2235.5833.28
SwinIRTraining strategy=Noise-specific (separate models)2023.0730.2235.6133.2
GRL-SMACs (G)=975, Inf. (ms)=680, Image Size=512 x 512 x 32024.0130.1835.3233.29
DRUNetTraining strategy=Noise-blind (various noise levels)2023.0730.0835.433.14
CODEMACs (G)=180, Inf. (ms)=600, Image Size=512 x 512 x 32024.0130.0335.3833.11
CODETraining strategy=Noise-specific (separate models)2023.0730.0335.3833.11
IPTTraining strategy=Noise-specific (separate models)2023.0729.98——
RNANTraining strategy=Noise-specific (separate models)2023.0729.72——
BRDNetTraining strategy=Noise-specific (separate models)2023.0729.5235.0832.75
RDNTraining strategy=Noise-specific (separate models)2023.0729.38——
DSNetTraining strategy=Noise-blind (various noise levels)2023.0729.2834.6732.4
FFDNetTraining strategy=Noise-blind (various noise levels)2023.0729.1834.6632.35
DnCNNTraining strategy=Noise-blind (various noise levels)2023.0728.6233.4531.52
CBM3DTraining strategy=Noise-blind (various noise levels)2023.0728.5134.0631.66