ruiliu-ai / FuseFormer

official Pytorch implementation of ICCV 2021 paper FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

about the stationary mask for youtube-vos and davis test dataset

Feynman1999 opened this issue · comments

how can i find the stationary test mask for the two datasets (for PSNR)? if you can release the masks and the results that your model generate, that would be better!!!

We randomly generate the free-form masks for evaluation, following https://github.com/JiahuiYu/generative_inpainting.

ok! I will check! can you add the pipeline (e.g. some code or directly masks pngs) to your readme, thanks!

can you upload the masks' download link to the github you used in the tabel2 directly? thanks!!!

The evaluation code is added and the README is updated.
Directly using our prepared stationary masks and evaluation code can achieve the exact results of table2.