What's the relationship between point clouds and features derived from point clouds? Particularly in CNN prediction.

Particularly, I have point clouds about which I can imagine features that are meaningful. Yet what has confused me is:

Should I do the train set so that it consists of features e.g. "size of a sub-cloud" (say, my point set is a vehicle, then a feature would be e.g. 'diameter of wheel').

Or do I compare point clouds to point clouds? I.e.I take sample wheel point clouds and then an algo matches those against new point clouds of wheels. How does this work, I've only found examples about training sets of "features", where a single feature column consists of only single values, e.g. a "percentage".


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.