Video Frame Interpolation on Middlebury (PSNR/SSIM/LPIPS)
38.83PSNROurs-triplets
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Ours-tripletstraining dataset=Vimeo-Triplets-Train, # Parameters (Million)=28.9, Runtime (ms)=6802022.03 | 38.83 | 0.989 | — | |
| SoftSplat-LLapTraining dataset=Vimeo-90K2021.03 | 38.42 | 0.971 | 0.016 | |
| SoftSplattraining dataset=Vimeo-Triplets-Train, # Parameters (Million)=7.7, Runtime (ms)=1352022.03 | 38.42 | 0.971 | — | |
| RIFE-Ltraining dataset=Vimeo-Triplets-Train, # Parameters (Million)=20.9, Runtime (ms)=722022.03 | 37.64 | 0.985 | — | |
| SoftSplat-LfTraining dataset=Vimeo-90K2021.03 | 37.55 | 0.965 | 0.008 | |
| SepConv++training dataset=Vimeo-Triplets-Train, self-ensembling=true2022.03 | 37.47 | — | — | |
| PWDNtraining dataset=Vimeo-Triplets-Train, # Parameters (Million)=7.82022.03 | 37.2 | — | — | |
| CDFITraining dataset=Vimeo-90K, Parameters (million)=4.982021.03 | 37.14 | 0.966 | 0.007 | |
| CtxSyn-LLapTraining dataset=proprietary2021.03 | 36.93 | 0.964 | 0.016 | |
| EDSCtraining dataset=Vimeo-Triplets-Train, # Parameters (Million)=8.9, Runtime (ms)=462022.03 | 36.8 | 0.983 | — | |
| BMBCTraining dataset=Vimeo-90K, Parameters (million)=11.02021.03 | 36.79 | 0.965 | 0.015 | |
| EDSC-LcTraining dataset=Vimeo-90K, Parameters (million)=8.92021.03 | 36.76 | 0.966 | 0.014 | |
| DAINTraining dataset=Vimeo-90K, Parameters (million)=24.022021.03 | 36.7 | 0.965 | 0.017 | |
| DAINtraining dataset=Vimeo-Triplets-Train, # Parameters (Million)=24.0, Runtime (ms)=1302022.03 | 36.7 | 0.965 | — | |
| BMBCtraining dataset=Vimeo-Triplets-Train, # Parameters (Million)=11.0, Runtime (ms)=15802022.03 | 36.66 | 0.983 | — | |
| EDSC-LfTraining dataset=Vimeo-90K, Parameters (million)=8.92021.03 | 36.48 | 0.963 | 0.007 | |
| AdaCoF+Training dataset=Vimeo-90K, Parameters (million)=22.93, F=11, d=22021.03 | 36.09 | 0.962 | 0.017 | |
| CtxSyn-LfTraining dataset=proprietary2021.03 | 35.95 | 0.959 | 0.013 | |
| SepConv-L1Training dataset=proprietary, Parameters (million)=21.62021.03 | 35.73 | 0.959 | 0.017 | |
| SepConvtraining dataset=proprietary, # Parameters (Million)=21.6, Runtime (ms)=512022.03 | 35.73 | 0.959 | — | |
| AdaCoFTraining dataset=Vimeo-90K, Parameters (million)=21.84, F=5, d=12021.03 | 35.72 | 0.959 | 0.019 | |
| TOFlowtraining dataset=Vimeo-Triplets-Train, # Parameters (Million)=1.1, Runtime (ms)=722022.03 | 35.29 | 0.956 | — | |
| CAINTraining dataset=Vimeo-90K, Parameters (million)=42.82021.03 | 35.11 | 0.951 | 0.019 | |
| SepConv-LfTraining dataset=proprietary, Parameters (million)=21.62021.03 | 35.03 | 0.954 | 0.013 |