/Patent Tracker
NvidiaPatent applicationAI & softwareInterest 6/10

Nvidia patents method to enlarge images using neural networks

Nvidia describes a technique that uses a type of computer program called a neural network to make small images larger without losing quality. The system uses specific mathematical steps to rebuild the details of the picture, ensuring the overall look and texture stay consistent even when the size increases.

Why it mattersThis could help software developers create tools that improve the resolution of photos or graphics, making them look sharper on high-quality screens.

In the filing’s own words

Apparatuses, systems, and techniques for texture synthesis from small input textures in images using convolutional neural networks. In at least one embodiment, one or more convolutional layers are used in conjunction with one or more transposed convolution operations to generate a large textured output image from a small input textured image while preserving global features and texture, according to various novel techniques described herein.

What exactly they claim (claim 1)

1 - 20. (canceled)

Facts

Company
Nvidia (NVIDIA Corporation)
Official title
TECHNIQUES TO USE A NEURAL NETWORK TO EXPAND AN IMAGE
Publication number
US20260289724A1
Application number
19559893
Filed
Mar 6, 2026
Published
Sep 24, 2026
Inventors
9
Claims
21

Classified under

G06T 3/4038 Physics & computingG06N 3/08 Physics & computingG06T 3/4046 Physics & computingG06T 7/40 Physics & computingG06V 10/454 Physics & computingG06V 10/54 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Nvidia 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.