Image Denoising on CBSD68 sigma=15 (test)
34.35PSNRVLU-Net
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| VLU-Netprotocol=one-by-one IR2025.03 | 34.35 | — | |
| PromptIRprotocol=one-by-one IR2025.03 | 34.34 | — | |
| InstructIRType=All-in-one (end-to-end), Params.=16M, Setting=NHR settings2025.03 | 34.15 | — | |
| InstructIRprotocol=one-by-one IR2025.03 | 34.15 | — | |
| AirNetprotocol=one-by-one IR2025.03 | 34.14 | — | |
| VLU-NetType=deep unfolding, Params.=35M, Setting=NHR settings2025.03 | 34.13 | — | |
| IDRprotocol=one-by-one IR2025.03 | 34.11 | — | |
| Restormerprotocol=one-by-one IR2025.03 | 34.03 | — | |
| NDRType=All-in-one (end-to-end), Params.=39M, Setting=NHR settings2025.03 | 34.01 | — | |
| PromptIRType=All-in-one (end-to-end), Params.=33M, Setting=NHR settings2025.03 | 33.98 | — | |
| GridformerType=All-in-one (end-to-end), Params.=34M, Setting=NHR settings2025.03 | 33.93 | — | |
| AirNetType=All-in-one (end-to-end), Params.=9M, Setting=NHR settings2025.03 | 33.92 | — | |
| DnCNNprotocol=one-by-one IR2025.03 | 33.9 | — | |
| IDRType=All-in-one (end-to-end), Params.=15M, Setting=NHR settings2025.03 | 33.89 | — | |
| MambaIRType=One-by-one (end-to-end), Params.=27M, Setting=NHR settings2025.03 | 33.88 | — | |
| FFDNetprotocol=one-by-one IR2025.03 | 33.87 | — | |
| DGUNetprotocol=one-by-one IR2025.03 | 33.85 | — | |
| RestormerType=One-by-one (end-to-end), Params.=26M, Setting=NHR settings2025.03 | 33.72 | — | |
| MeDTraining Schema=Random variance (sigma in [5, 50]), Training Paradigm=Invariant Feature2023.09 | 33.62 | 0.9026 | |
| DBD4Training Schema=Fixed variance (sigma=25), Training Paradigm=Noisy/Clean2023.09 | 33.57 | 0.9092 | |
| N2CTraining Schema=Random variance (sigma in [5, 50]), Training Paradigm=Noisy/Clean2023.09 | 33.47 | 0.9027 | |
| N2NTraining Schema=Random variance (sigma in [5, 50]), Training Paradigm=N2N2023.09 | 33.45 | 0.8945 | |
| N2CTraining Schema=Fixed variance (sigma=25), Training Paradigm=Noisy/Clean2023.09 | 33.36 | 0.902 | |
| SwinIRprotocol=one-by-one IR2025.03 | 33.31 | — | |
| MPRNetType=One-by-one (end-to-end), Params.=16M, Setting=NHR settings2025.03 | 33.27 | — | |
| DBD4Training Schema=Random variance (sigma in [5, 50]), Training Paradigm=Noisy/Clean2023.09 | 33.12 | 0.8915 | |
| MeDTraining Schema=Fixed variance (sigma=25), Training Paradigm=Invariant Feature2023.09 | 33.11 | 0.888 | |
| N2STraining Schema=Fixed variance (sigma=25), Training Paradigm=Noisy/Noisy2023.09 | 32.77 | 0.878 | |
| N2NTraining Schema=Fixed variance (sigma=25), Training Paradigm=N2N2023.09 | 32.64 | 0.8805 | |
| N2STraining Schema=Random variance (sigma in [5, 50]), Training Paradigm=Noisy/Noisy2023.09 | 31.28 | 0.8187 | |
| LIRTraining Schema=Fixed variance (sigma=25), Training Paradigm=Invariant Feature2023.09 | 31.06 | 0.8632 | |
| LIRTraining Schema=Random variance (sigma in [5, 50]), Training Paradigm=Invariant Feature2023.09 | 30.85 | 0.8431 | |
| R2RTraining Schema=Fixed variance (sigma=25), Training Paradigm=Noisy/Noisy2023.09 | 29.74 | 0.7865 | |
| R2RTraining Schema=Random variance (sigma in [5, 50]), Training Paradigm=Noisy/Noisy2023.09 | 20.76 | 0.2508 |