IDiyas

For the Inventor, By the Inventor

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.:

US 11776204 B1

PDFFull Text
Date of Patent:
Oct. 03, 2023

Filed:

Jan. 21, 2021

3d dataset generation for neural network model training

Applicant:

Sony Group Corporation, Tokyo, JP;

Inventors:

Jong Hwa Lee, San Diego, CA (US);

Seunghan Kim, San Diego, CA (US);

Gary Lyons, San Diego, CA (US);

Assignee:

SONY GROUP CORPORATION, Tokyo, JP;

Attorney:

CHIP LAW GROUP

Primary Examiner:

Sing-Wai Wu

Int. Cl.
CPC ...
G06T 17/00 (2006.01); G06N 3/08 (2023.01); G06T 7/529 (2017.01); G06T 19/20 (2011.01); G06V 40/16 (2022.01); G06T 17/10 (2006.01); G06F 18/214 (2023.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 10/54 (2022.01); G06V 10/44 (2022.01); G06V 20/64 (2022.01); G06V 40/10 (2022.01);
U.S. Cl.
CPC ...
G06T 17/00 (2013.01); G06F 18/214 (2023.01); G06N 3/08 (2013.01); G06T 7/529 (2017.01); G06T 17/10 (2013.01); G06T 19/20 (2013.01); G06V 10/44 (2022.01); G06V 10/54 (2022.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 20/647 (2022.01); G06V 40/10 (2022.01); G06V 40/171 (2022.01);
Abstract

An electronic device receives a set of 2D images comprising at least first 2D image of an object of interest and detects a plurality of 2D landmarks on the first 2D image. The detected plurality of 2D landmarks corresponds to shape-features of the object of interest. The electronic device aligns a first three-dimensional (3D) shape model of a reference object by fitting 2D landmarks of the first 3D shape model to the detected plurality of 2D landmarks. The electronic device estimates texture mapping information between the object of interest and the aligned first 3D shape model and generates a dataset by including the first 2D image, the aligned first 3D shape model, and the estimated texture mapping information as a first sample of the dataset. Based on the generated dataset, the electronic device trains a neural network model on a task of 3D reconstruction from a single 2D image.

Find Patent Forward Citations

Loading…