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:
Mar. 12, 2024

Filed:

Feb. 23, 2022
Applicant:

Autodesk, Inc., San Francisco, CA (US);

Inventors:

Thomas Ryan Davies, Toronto, CA;

Michael Haley, San Rafael, CA (US);

Ara Danielyan, Toronto, CA;

Morgan Fabian, Corona Del Mar, CA (US);

Assignee:

AUTODESK, INC., San Francisco, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06T 15/20 (2011.01); G06F 30/00 (2020.01); G06N 3/04 (2023.01); G06N 3/088 (2023.01);
U.S. Cl.
CPC ...
G06T 15/20 (2013.01); G06F 30/00 (2020.01); G06N 3/04 (2013.01); G06N 3/088 (2013.01);
Abstract

In various embodiments, a training application generates a trained encoder that automatically generates shape embeddings having a first size and representing three-dimensional (3D) geometry shapes. First, the training application generates a different view activation for each of multiple views associated with a first 3D geometry based on a first convolutional neural network (CNN) block. The training application then aggregates the view activations to generate a tiled activation. Subsequently, the training application generates a first shape embedding having the first size based on the tiled activation and a second CNN block. The training application then generates multiple re-constructed views based on the first shape embedding. The training application performs training operation(s) on at least one of the first CNN block and the second CNN block based on the views and the re-constructed views to generate the trained encoder.


Find Patent Forward Citations

Loading…