Hello, I observed on your code that when Rt is calculated according to the point correspondence, it is solved by SVD. But is the loss obtained in this way derivable?
PyTorch's implementation of SVD is differentiable, as seen here, allowing us to define losses using the estimated Rt and back propagating the loss to the features.
Hello, I observed on your code that when Rt is calculated according to the point correspondence, it is solved by SVD. But is the loss obtained in this way derivable?
https://github.com/mbanani/unsupervisedRR/blob/4ba5b1cc76080f5c6fd99cec155453f43b547bcd/unsupervisedRR/models/alignment.py#L127