What is the purpose of the non-uniform penalty?

[DandiC]

Hi @ranahanocka, I was wondering if you could explain what is the purpose of adding the "non-uniform" penalty to the loss during training. I see that the penalty is computed based on the areas of the face, but I don't know the reasoning behind it and I couldn't find any details in your paper.

point2mesh/main.py

Line 60 in 333dba0

loss += opts.local_non_uniform * local_nonuniform_penalty(part_mesh.main_mesh).float()

Thanks!