/Patent Tracker
GooglePatent applicationAI & softwareInterest 8/10

Google patents method to create 3D objects from text prompts

Patent drawing
Patent drawing from the official filing.

This filing describes a computer method that turns a text description into a 3D model by first generating two flat images from different angles. It uses probability calculations to ensure the features in these images match the original description before combining them into a single 3D representation.

Why it mattersThis could make it easier for creators to build 3D assets for games or design work using only text commands instead of manual modeling.

In the filing’s own words

A computer-implemented method includes generating a first two-dimensional image of an object based on a prompt describing the object, and a transformation of a first representation of the object based on a probability of a first feature being included in the first two-dimensional image of the object, the probability of the first feature being based on the first representation of the object and at least two sample two-dimensional images; generating a second two-dimensional image of the object from a different perspective than the first two-dimensional image of the object by transforming a second representation of the object based on the first two-dimensional image and a probability of a second feature being included in the second two-dimensional image of the object; and generating a three-dimensional representation of the object based on the first two-dimensional image of the object and the second two-dimensional image of the object.

What exactly they claim (claim 1)

1. A computer-implemented method comprising: generating a first two-dimensional image of an object based on: a prompt describing the object; and a transformation of a first representation of the object based on a probability of a first feature being included in the first two-dimensional image of the object, the probability of the first feature being based on the first representation of the object and at least two sample two-dimensional images; generating a second two-dimensional image of the object from a different perspective than the first two-dimensional image of the object by transforming a second representation of the object based on the first two-dimensional image and a probability of a second feature being included in the second two-dimensional image of the object; and generating a three-dimensional representation of the object based on the first two-dimensional image of the object and the second two-dimensional image of the object.

Facts

Company
Google (GOOGLE LLC)
Official title
GENERATING THREE-DIMENSIONAL REPRESENTATION OF OBJECT BASED ON PROMPT
Publication number
US20260320908A1
Application number
19644373
Filed
Apr 10, 2026
Published
Oct 15, 2026
Inventors
6
Claims
20

Classified under

G06T 15/205 Physics & computingG06T 7/194 Physics & computingG06T 17/20 Physics & computingG06T 2207/20076 Physics & computingG06T 2207/30244 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Google in AI & software

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.