PhyCell_Cell code is different comparing to the paper

[sippeyxp]

In paper K is a function of h_tilde_t and E(u_t).

In code, the implementation is

24 combined = torch.cat([x, hidden], dim=1) # concatenate along channel axis
25 combined_conv = self.convgate(combined)
26 K = torch.sigmoid(combined_conv)

On line 24, it should be torch.cat([x, hidden_tilde, dim=1) ?

[lf-demo]

I have the same question with you at first. But i find that the detail of experiment is recorded in the supplementary. Here is the link https://openaccess.thecvf.com/content_CVPR_2020/supplemental/Le_Guen_Disentangling_Physical_Dynamics_CVPR_2020_supplemental.pdf