James Fury

About the hear map mentioned in paper.

1

Hi , is there any possible for you to provide the code for heat map mentioned in paper?

Hi, thanks for the great work! I didn't figure out the code below `flow_n2 = flow_n1 + flow_warp( flow_n2, flow_n1.permute(0, 2, 3, 1))`

Is there any pretrained weights provided?

one called SpatialLinearAttention, the other is normal attention.

Is there any pertrained model?

2

Is there any pertrained model?

Warp flow by flow

1

Hi , thanks for your great work. I want to figure out the code `flow_n2 = flow_n1 + flow_warp(flow_n2, flow_n1.permute(0, 2, 3, 1))`

hi， thanks four great work， Is it possible to have a pytorch version of the implementation?

Is there any scripts for SSIM metrics ?

Hi , About the formula 12 in the paper Si,j is the cosine similarity results, which use the + 1 and the formula 12 in the paper Di,j also s...

Hi , i want to konw the VGG encoder is pre-trained on which dataset? MScoco?