/Patent Tracker
GoogleGranted patentAI & softwareInterest 4/10

Google patents method to expand image training data by recoloring

Google describes a technique for creating more training data for image processing models. It works by turning images into grayscale and then using separate colorization models to add different colors back in, creating new variations of the original pictures.

Why it mattersThis helps computer vision systems learn from a wider variety of images without needing to manually collect or label more real-world photos.

In the filing’s own words

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating, using one or more coloraF_ization models, an augmented set of training data. One of the methods includes receiving a plurality of training examples for training an image processing model, each training example comprising an image and a corresponding ground-truth output for the image; generating, for each image, a respective grayscale image; generating, for each respective grayscale image, one or more recolored images using one or more colorization models; and generating an augmented set of training data for training the image processing model that comprises a plurality of additional training examples.

What exactly they claim (claim 1)

1. A computer-implemented method comprising: receiving a plurality of training examples for training an image processing model, each training example comprising a synthetic image and a corresponding ground-truth output for the synthetic image; generating, for each synthetic image, a respective grayscale image; generating, for each respective grayscale image, one or more recolored images using one or more colorization models, wherein each colorization model is different than the image processing model; and generating an augmented set of training data for training the image processing model that comprises a plurality of additional training examples, each additional training example comprising a respective recolored image generated from a respective synthetic image and the corresponding ground-truth output for the respective synthetic image.

Facts

Company
Google (Google LLC)
Official title
Augmenting training data by recoloring images
Patent number
US12755447B2
Application number
18626179
Filed
Apr 3, 2024
Granted
Oct 6, 2026
Inventors
7
Claims
20

Classified under

G06T 11/10 Physics & computingG06T 3/40 Physics & computingG06T 7/90 Physics & computingG06T 2207/10024 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.