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:
Jul. 28, 2026

Filed:

Feb. 17, 2025
Applicant:

Nvidia Corporation, Santa Clara, CA (US);

Inventors:

Bowen Wen, Issaquah, WA (US);

Matthew Trepte, San Francisco, CA (US);

Orazio Gallo, Santa Cruz, CA (US);

Jan Kautz, Lexington, MA (US);

Stanley Thomas Birchfield, Sammamish, WA (US);

Assignee:

NVIDIA Corporation, Santa Clara, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06T 7/593 (2017.01); G06T 7/62 (2017.01); G06T 7/73 (2017.01); H04N 13/128 (2018.01); H04N 13/194 (2018.01); H04N 13/271 (2018.01); H04N 13/00 (2018.01);
U.S. Cl.
CPC ...
G06T 7/593 (2017.01); G06T 7/62 (2017.01); G06T 7/74 (2017.01); H04N 13/128 (2018.05); H04N 13/194 (2018.05); H04N 13/271 (2018.05); G06T 2207/10012 (2013.01); G06T 2207/20016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20228 (2013.01); H04N 2013/0081 (2013.01);
Abstract

Systems and methods are disclosed that use a Foundational Stereo Model to generate an output disparity map. The Foundational Stereo Model includes side-tuning adapters (STA) that utilize a vision transformer (ViT) and a convolutional neural network (CNN) to generate feature maps. Specifically, the CNN may be used to adapt the ViT-based monocular depth estimation network for the stereo setup, which synergizes the strengths of both CNN and ViT architectures. In addition, the Foundational Stereo Model includes an attentive hybrid cost filtering (AHCF) that uses two branches that also utilizes the advantages of both a transformer architecture and the CNN architecture. Furthermore, the Foundational Stereo Model may perform iterative refinement of an initial disparity map to obtain the output disparity map based on performing a convolutional gated recurrent unit (GRU) operation.


Find Patent Forward Citations

Loading…