Blind Deconvolution on Levin alpha=10 realistic camera shake blur
22.41PSNRPhD-Net
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| PhD-NetBlind deconvolution=false, End-To-End Trained=true2023.03 | 22.41 | 63.8 | 0.341 | 0.466 | |
| Kernel Trajectory NetworkBlind deconvolution=true, End-To-End Trained=false2023.03 | 22.01 | 61.1 | 0.34 | 0.477 | |
| PURE-LETBlind deconvolution=false, End-To-End Trained=false2023.03 | 21.63 | 59 | 0.371 | 0.522 | |
| MIMO-UNet+Blind deconvolution=true, End-To-End Trained=true2023.03 | 21.25 | 51.6 | 0.594 | 0.661 | |
| MPRNetBlind deconvolution=true, End-To-End Trained=true2023.03 | 21.04 | 53.3 | 0.479 | 0.511 | |
| Deep-DeblurBlind deconvolution=true, End-To-End Trained=true2023.03 | 20.93 | 52.4 | 0.496 | 0.518 | |
| DHMPNBlind deconvolution=true, End-To-End Trained=true2023.03 | 20.5 | 50.9 | 0.521 | 0.526 | |
| SRNBlind deconvolution=true, End-To-End Trained=true2023.03 | 20.26 | 51 | 0.507 | 0.531 | |
| P4IPBlind deconvolution=false, End-To-End Trained=false2023.03 | 19.92 | 46.3 | 0.546 | 0.555 |