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. 03, 2025

Filed:

Dec. 14, 2023
Applicant:

Google Llc, Mountain View, CA (US);

Inventors:

Melissa Strader, San Jose, CA (US);

William Ito, Mountain View, CA (US);

Christopher Co, Saratoga, CA (US);

Katherine Chou, Palo Alto, CA (US);

Alvin Rajkomar, San Jose, CA (US);

Rebecca Rolfe, Menlo Park, CA (US);

Assignee:

Google LLC, Mountain View, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G16H 50/20 (2018.01); G06F 16/334 (2025.01); G06F 40/279 (2020.01); G10L 15/00 (2013.01); G10L 15/08 (2006.01); G10L 17/00 (2013.01); G16H 10/60 (2018.01); G16H 40/63 (2018.01); G16H 50/70 (2018.01);
U.S. Cl.
CPC ...
G16H 50/20 (2018.01); G06F 16/3344 (2019.01); G06F 40/279 (2020.01); G10L 15/00 (2013.01); G10L 15/005 (2013.01); G10L 15/08 (2013.01); G16H 10/60 (2018.01); G16H 40/63 (2018.01); G16H 50/70 (2018.01); G10L 2015/088 (2013.01); G10L 17/00 (2013.01);
Abstract

A computer-implemented method includes receiving, by a computing device, a particular textual description of a scene. The method also includes applying a neural network for text-to-image generation to generate an output image rendition of the scene, the neural network having been trained to cause two image renditions associated with a same textual description to attract each other and two image renditions associated with different textual descriptions to repel each other based on mutual information between a plurality of corresponding pairs, wherein the plurality of corresponding pairs comprise an image-to-image pair and a text-to-image pair. The method further includes predicting the output image rendition of the scene.


Find Patent Forward Citations

Loading…