What is the meaning of “refine_init” in displacement estimation?

[Devoe-97]

Hello, thanks for this great repo. I have a question about what “refine_init” means in the code.

RoMa/romatch/models/matcher.py

Line 397 in 3701174

displacement = ins*torch.stack((delta_flow[:, 0].float() / (self.refine_init * w),

[Parskatt]

This is inherited from DKM. My thought then was that that if the output of the network is std=1 this normalization means that outputs are scaled to about 1/4 of the current pixel size on average. I haven't looked if it has any impact. In general its probably good to init the output of the refiners to be near 0 since theyre applied recursively.

[Devoe-97]

This is inherited from DKM. My thought then was that that if the output of the network is std=1 this normalization means that outputs are scaled to about 1/4 of the current pixel size on average. I haven't looked if it has any impact. In general its probably good to init the output of the refiners to be near 0 since theyre applied recursively.

Thanks!