List your company
ResearchFormerly WizWand

Video Frame Interpolation on X (test)

30.81PSNRM2M-PWC
25.266826.705928.14529.5841Nov 25, 2022
Updated 8mo ago

Evaluation results

MethodLinks
M2M-PWCPretrained flow=true, # Param. (Mill.)=7.6, Memory (for 4K)=10 GB, Training dataset=Vimeo90K, Inference (in s/f)=0.212022.1130.81——
fLDR-NetPretrained flow=false, # Param. (Mill.)=0.9, Memory (for 4K)=4.6 GB, Training dataset=X-Train, Inference (in s/f)=0.512022.1130.45——
XVFIPretrained flow=false, # Param. (Mill.)=5.5, Memory (for 4K)=>12 GB, Training dataset=X-Train2022.1130.34——
M2M-DISPretrained flow=true, Training dataset=Vimeo90K2022.1130.18——
ABMEPretrained flow=false, # Param. (Mill.)=18.1, Training dataset=Vimeo90K2022.1130.16——
RIFEmPretrained flow=false, # Param. (Mill.)=9.8, Memory (for 4K)=6.8 GB, Training dataset=X-Train, Inference (in s/f)=0.402022.1128.06——
RIFEmPretrained flow=false, # Param. (Mill.)=9.8, Memory (for 4K)=6.8 GB, Training dataset=Vimeo90K, Inference (in s/f)=0.402022.1126.8——
SoftSplatPretrained flow=true, # Param. (Mill.)=7.7, Training dataset=Vimeo90K2022.1125.48——
fLDR-NetInference (in s/f)=0.50*/0.512022.11—0.8710.099
M2M-PWCInference (in s/f)=0.212022.11—0.9140.086
RIFElInference (in s/f)=0.402022.11—0.7930.227
RIFEmInference (in s/f)=0.402022.11—0.7510.26
XVFIInference (in s/f)=0.66*/N/A2022.11—0.8740.085