Thank you very much for publishing your code. Very interesting work.
I am interested in using the rendering pipeline for batched computation. More exactly, suppose I have a tensor of size B x NxNxN
which represents a mini batch of data containing B SDF grids of size N^3. My understanding is that the current implementation does not support batch computation (and I would need to do the computation in a loop). I was wondering if my understanding is correct, and if so, if there is any easy way to modify the implementation to support this feature.
Thank you very much for publishing your code. Very interesting work.
I am interested in using the rendering pipeline for batched computation. More exactly, suppose I have a tensor of size
B x NxNxN
which represents a mini batch of data containingB
SDF grids of sizeN^3
. My understanding is that the current implementation does not support batch computation (and I would need to do the computation in a loop). I was wondering if my understanding is correct, and if so, if there is any easy way to modify the implementation to support this feature.Thanks,