Hello,

I have implemented various preprocessing functions in tensorflow, compatible with tf.data.Dataset API for augmenting pointclouds including jitter, random_cutout, random_translation, random_rotation, random_zoom, etc..

I was curious to know if they would fall in the scope of tfg so I could submit a PR.

These could be implemented as augmentation layers just like keras-cv augmentations. I am not sure if these fall into the scope of tfg or keras-cv