ALEXANDRIA, Va., Nov. 6 -- United States Patent no. 12,462,438, issued on Nov. 4, was assigned to Dassault Systemes (Velizy-Villacoublay, France).
"Machine-learning for 3D object detection" was invented by Asma Rejeb Sfar (Velizy-Villacoublay, France), Tom Durand (Velizy-Villacoublay, France) and Ashad Hosenbocus (Velizy-Villacoublay, France).
According to the abstract* released by the U.S. Patent & Trademark Office: "A computer-implemented method of machine-learning for learning a neural network that encodes a super-point of a 3D point cloud into a latent vector. The method including obtaining a dataset of super-points. Each super-point is a set of points of a 3D point cloud. The set of points represents at least a part of an object. The...