Different evalutaion result on UCF dataset using frames generated by run.py

[MintcakeDotCom]

Hi!

I used run.py to generate interpolated frames on UCF101 dataset first and then calculated average PSNR. However, there is a little difference between my result and yours from the paper. The model I use is CyclicGen_model.py and I also test your result images. Without motion mask, the difference is around 0.4dB. So is it because of the motion mask or other fact that has influence on the result images?

[alex04072000]

I don't think there are other factors that will change the PSNR. Please apply the motion masks and calculate the PSNR again to see whether the result match the paper. I also suggest you to use the evaluation code from DVF to avoid some minor implementation differences. Thank you!

[MintcakeDotCom]

Thanks for your reply, I'll try to add motion masks to result images and compare the PSNR. Also I'll look into the eval code from DVF. Thank you!