/Patent Tracker
GooglePatent applicationAI & softwareInterest 7/10

Google patents method to restore old photos using AI diffusion models

Google describes a process that fixes blurry or damaged photos by running them through a computer model multiple times. Each step combines the current image with a prediction of what the final picture should look like and a bit of random noise to gradually improve the quality.

Why it mattersThis could lead to better tools for cleaning up old family photos or fixing low-resolution images without needing a perfect original file.

In the filing’s own words

Provided is an iterative image restoration process using low-quality images paired with the desired high-quality restored image as training data for the one or more image restoration models.

What exactly they claim (claim 1)

1. A computer-implemented method for performing digital image restoration the method comprising: receiving a degraded image, wherein the degraded image is used as an initial image for a current image for processing; for each step in a specified number of steps: inputting the current image into the image restoration model; receiving, from the image restoration model, a prediction of a final image based on the input current image; combining the current image, the prediction of the final image, and a noise sample into an output image; and setting a state of the current image to the output image; and after the specified number of steps have been performed, outputting the current image as a restored image.

Facts

Company
Google (Google LLC)
Official title
Digital Image Restoration Using Diffusion Models
Publication number
US20260268453A1
Application number
19167692
Filed
Mar 20, 2024
Published
Sep 10, 2026
Inventors
2
Claims
20

Classified under

G06T 5/60 Physics & computingG06T 5/50 Physics & computingG06T 2207/20081 Physics & computingG06T 2207/20221 Physics & computing

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.