3d pointclouds in pytorch

I am really confused to know whether tensor flow or pytorch is better in handling 3d pointclouds for classification or semantic segmentation purposes. I have just started using pytorch and could find it is mainly for images or 2d data. Couldnot find examples for 3d in pytorch. What is the advantage of using pytorch for 3d instead of tensorflow? Can anyone clarify this please?

1 Like