A system configured to process an input point cloud, which represents an object using unstructured data points, to generate a feature vector that has an ordered structure and a fixed length. The system may process the input point cloud using a basis point set to generate the feature vector. For example, 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. The system may process the feature vector using a trained model to generate output data, such as performing point cloud registration to generate mesh data, point cloud classification to generate classification data, and/or the like.
d?(bk,xij)]T,XiB∈k???d[5]
where XiB is the feature vector, bi denotes a basis point, xij denotes a data point in the point cloud data, k denotes the fixed number of basis points, and d=3 for 3D point cloud data.