The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Nov. 04, 2025

Filed:

Dec. 16, 2021
Applicant:

Dassault Systemes, Vélizy-Villacoublay, FR;

Inventors:

Asma Rejeb Sfar, Vélizy-Villacoublay, FR;

Tom Durand, Vélizy-Villacoublay, FR;

Ashad Hosenbocus, Vélizy-Villacoublay, FR;

Assignee:

Dassault Systemes, Velizy-Villacoublay, FR;

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06T 9/00 (2006.01); G06N 3/088 (2023.01); G06V 10/74 (2022.01); G06V 10/82 (2022.01);
U.S. Cl.
CPC ...
G06T 9/002 (2013.01); G06N 3/088 (2013.01); G06V 10/761 (2022.01); G06V 10/82 (2022.01);
Abstract

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 method further includes learning the neural network based on the dataset of super-points. The learning includes minimizing a loss. The loss penalizes a disparity between two super-points. This constitutes improved machine-learning for 3D object detection.


Find Patent Forward Citations

Loading…