URSA: A Neural Network for Unordered Point Clouds Using Constellations
This addresses the challenge of building efficient classifiers for unordered point cloud data, which is incremental as it improves parameter efficiency while maintaining performance.
The paper tackles the problem of classifying unordered point clouds by introducing Ursa, a neural network layer that is agnostic to point ordering while preserving dimensional information, achieving classification results comparable to current methods on ModelNet40 and MNIST data with over 50% fewer training parameters.
This paper describes a neural network layer, named Ursa, that uses a constellation of points to learn classification information from point cloud data. Unlike other machine learning classification problems where the task is to classify an individual high-dimensional observation, in a point-cloud classification problem the goal is to classify a set of d-dimensional observations. Because a point cloud is a set, there is no ordering to the collection of points in a point-cloud classification problem. Thus, the challenge of classifying point clouds inputs is in building a classifier which is agnostic to the ordering of the observations, yet preserves the d-dimensional information of each point in the set. This research presents Ursa, a new layer type for an artificial neural network which achieves these two properties. Similar to new methods for this task, this architecture works directly on d-dimensional points rather than first converting the points to a d-dimensional volume. The Ursa layer is followed by a series of dense layers to classify 2D and 3D objects from point clouds. Experiments on ModelNet40 and MNIST data show classification results comparable with current methods, while reducing the training parameters by over 50 percent.