Pointwise Cylinder Refinement Model
Closed this issue · 1 comments
L-Reichardt commented
Hello,
I have a question about the Pointnet that generates the Cylinder features. Is there any particular reason why the input tensor has the dimension (N, 9) not (N, 3)? Do I understand correctly that this is contains the (polar coordinate points centered in voxels)(points in polar coordinates)(pointcloud)?
Also why is the data shuffled?
L-Reichardt commented
No need for answer anymore.