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:
Jun. 09, 2026

Filed:

Sep. 22, 2023
Applicant:

Nvidia Corporation, Santa Clara, CA (US);

Inventors:

Koki Nagano, Playa Vista, CA (US);

Alexander Trevithick, Mamaroneck, NY (US);

Chao Liu, Pittsburgh, PA (US);

Eric Ryan Chan, Alameda, CA (US);

Sameh Khamis, Alameda, CA (US);

Michael Stengel, Hayward, CA (US);

Zhiding Yu, Santa Clara, CA (US);

Assignee:

NVIDIA Corporation, Santa Clara, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06T 17/00 (2006.01); G06T 5/20 (2006.01); G06T 7/70 (2017.01); G06T 7/90 (2017.01); G06V 10/771 (2022.01);
U.S. Cl.
CPC ...
G06T 17/00 (2013.01); G06T 5/20 (2013.01); G06T 7/70 (2017.01); G06T 7/90 (2017.01); G06V 10/771 (2022.01); G06T 2207/10024 (2013.01);
Abstract

A method for generating, by an encoder-based model, a three-dimensional (3D) representation of a two-dimensional (2D) image is provided. The encoder-based model is trained to infer the 3D representation using a synthetic training data set generated by a pre-trained model. The pre-trained model is a 3D generative model that produces a 3D representation and a corresponding 2D rendering, which can be used to train a separate encoder-based model for downstream tasks like estimating a triplane representation, neural radiance field, mesh, depth map, 3D key points, or the like, given a single input image, using the pseudo ground truth 3D synthetic training data set. In a particular embodiment, the encoder-based model is trained to predict a triplane representation of the input image, which can then be rendered by a volume renderer according to pose information to generate an output image of the 3D scene from the corresponding viewpoint.


Find Patent Forward Citations

Loading…