search

shleecs / Copy-and-Paste-Networks-for-Deep-Video-Inpainting

Official Pytorch implementation of Copy-and-Paste Networks for Deep Video Inpainting (ICCV 2019)
118 stars 18 forks source link

Training Details #6

Open vishnusanjayrs opened 4 years ago

vishnusanjayrs commented 4 years ago

Hi Sungho,

Thanks for the amazing work and package.

In the paper : "We train with the randomly selected five 256 × 256 frames from the synthesized video sequences as inputs"

Does it mean you used 5 reference frames for each target frame ? Can you please clarify?