To improve efficiency, reduce an amount of data, and reduce computational processing required to process point cloud data, devices, systems and methods are disclosed that may process point cloud data using basis point sets. The system may process the point cloud data using a basis point set to generate a feature vector (e.g., distance data) that has an ordered structure with a fixed length. The system may then process the feature vector using a trained model to perform various tasks, such as point cloud registration to generate mesh data, point cloud classification to generate classification data, and/or the like. For each basis point in the basis point set, the system may identify a closest data point in the point cloud data and store a distance value or other information associated with the closest data point in the feature vector.

FIG. 1 illustrates a high-level conceptual block diagram of a system 100 configured to process point clouds using machine learning algorithms according to embodiments of the present disclosure. Although FIG. 1, and other figures/discussion illustrate the operation of the system in a particular order, the steps described may be performed in a different order (as well as certain steps removed or added) without departing from the intent of the disclosure. A plurality of devices may communicate across one or more network(s) 10. For example, FIG. 1 illustrates an example of a device 110 local to a user 5 communicating with a remote system 120 via the network(s) 10.