List your company
ResearchFormerly WizWand

Image Denoising on CBSD68 sigma=15 (test)

34.35PSNRVLU-Net
20.216423.885727.55531.2243Sep 10, 2023Dec 12, 2023Mar 14, 2024Jun 15, 2024Sep 16, 2024Dec 18, 2024Mar 21, 2025
Updated 8mo ago

Evaluation results

MethodLinks
VLU-Netprotocol=one-by-one IR2025.0334.35—
PromptIRprotocol=one-by-one IR2025.0334.34—
InstructIRType=All-in-one (end-to-end), Params.=16M, Setting=NHR settings2025.0334.15—
InstructIRprotocol=one-by-one IR2025.0334.15—
AirNetprotocol=one-by-one IR2025.0334.14—
VLU-NetType=deep unfolding, Params.=35M, Setting=NHR settings2025.0334.13—
IDRprotocol=one-by-one IR2025.0334.11—
Restormerprotocol=one-by-one IR2025.0334.03—
NDRType=All-in-one (end-to-end), Params.=39M, Setting=NHR settings2025.0334.01—
PromptIRType=All-in-one (end-to-end), Params.=33M, Setting=NHR settings2025.0333.98—
GridformerType=All-in-one (end-to-end), Params.=34M, Setting=NHR settings2025.0333.93—
AirNetType=All-in-one (end-to-end), Params.=9M, Setting=NHR settings2025.0333.92—
DnCNNprotocol=one-by-one IR2025.0333.9—
IDRType=All-in-one (end-to-end), Params.=15M, Setting=NHR settings2025.0333.89—
MambaIRType=One-by-one (end-to-end), Params.=27M, Setting=NHR settings2025.0333.88—
FFDNetprotocol=one-by-one IR2025.0333.87—
DGUNetprotocol=one-by-one IR2025.0333.85—
RestormerType=One-by-one (end-to-end), Params.=26M, Setting=NHR settings2025.0333.72—
MeDTraining Schema=Random variance (sigma in [5, 50]), Training Paradigm=Invariant Feature2023.0933.620.9026
DBD4Training Schema=Fixed variance (sigma=25), Training Paradigm=Noisy/Clean2023.0933.570.9092
N2CTraining Schema=Random variance (sigma in [5, 50]), Training Paradigm=Noisy/Clean2023.0933.470.9027
N2NTraining Schema=Random variance (sigma in [5, 50]), Training Paradigm=N2N2023.0933.450.8945
N2CTraining Schema=Fixed variance (sigma=25), Training Paradigm=Noisy/Clean2023.0933.360.902
SwinIRprotocol=one-by-one IR2025.0333.31—
MPRNetType=One-by-one (end-to-end), Params.=16M, Setting=NHR settings2025.0333.27—
DBD4Training Schema=Random variance (sigma in [5, 50]), Training Paradigm=Noisy/Clean2023.0933.120.8915
MeDTraining Schema=Fixed variance (sigma=25), Training Paradigm=Invariant Feature2023.0933.110.888
N2STraining Schema=Fixed variance (sigma=25), Training Paradigm=Noisy/Noisy2023.0932.770.878
N2NTraining Schema=Fixed variance (sigma=25), Training Paradigm=N2N2023.0932.640.8805
N2STraining Schema=Random variance (sigma in [5, 50]), Training Paradigm=Noisy/Noisy2023.0931.280.8187
LIRTraining Schema=Fixed variance (sigma=25), Training Paradigm=Invariant Feature2023.0931.060.8632
LIRTraining Schema=Random variance (sigma in [5, 50]), Training Paradigm=Invariant Feature2023.0930.850.8431
R2RTraining Schema=Fixed variance (sigma=25), Training Paradigm=Noisy/Noisy2023.0929.740.7865
R2RTraining Schema=Random variance (sigma in [5, 50]), Training Paradigm=Noisy/Noisy2023.0920.760.2508