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.
Patent No.:
Date of Patent:
Jun. 02, 2026
Filed:
Jan. 16, 2024
Dassault Systemes, Velizy Villacoublay, FR;
Ecole Polytechnique, Palaiseau Cedex, FR;
Centre National DE LA Recherche Scientifique, Paris Cedex, FR;
Mariem Mezghanni, Vélizy-Villacoublay, FR;
Kawtar Zaher, Vélizy-Villacoublay, FR;
Malika Boulkenafed, Vélizy-Villacoublay Cedex, FR;
Maks Ovsjanikov, Palaiseau Cedex, FR;
DASSAULT SYSTEMES, Vélizy Villacoublay, FR;
ECOLE POLYTECHNIQUE, Palaiseau Cedex, FR;
CENTRE NATIONAL DE LA RECHERCHE SCIENTIFIQUE, Paris Cedex, FR;
Abstract
A computer-implemented method of machine-learning. The method includes obtaining a training dataset of 3D models of real-world objects. The method further includes learning, based on the training dataset and on a patch-decomposition of the 3D models of the training dataset, a finite codebook of quantized vectors and a neural network. The neural network comprises a rotation-invariant encoder. The rotation-invariant encoder is configured for rotation-invariant encoding of a patch of a 3D model into a quantized latent vector of the codebook. The neural network further includes a decoder. The decoder is configured for decoding a sequence of quantized latent vectors of the codebook into a 3D model. The sequence corresponds to a patch-decomposition. This constitutes an improved solution for 3D model generation.