Why is it necessary to add the identity matrix in the transeform.py

[ShichaoJin]

[pmorerio]

I was asking myself the same. In the supplementary material of the paper they mention that

The output matrix is initialized as an identity matrix

I guess this is a way of initializing the transformation very close to the identity. The transformation is then learned in a "residual" fashion (i.e. the matrix is actually parameterized as 1+M). This is the answer I could provide myself. It would be nice to have a confirmation from the authors.

[adosar]

@pmorerio This is also what I am thinking. I was confused with the term initialized since this matrix is always initialized/added at each step (both at training and inference).