Google patents method to create lighting data for image models
Google describes a system that takes pairs of photos showing a scene under different lighting conditions and uses them to create new, synthetic images with altered lighting. These generated images are then added to a dataset to help train computer models that can edit or generate pictures with specific light changes.
In the filing’s own words
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for obtaining a plurality of training examples, each training example comprising a respective first image depicting a corresponding scene when a target light source is in a first state and a respective second image depicting the corresponding scene when the target light source is in a second state; generating, for each training example, a plurality of respective modified images that each depict the corresponding scene when the target light source is in a respective modified state; and generating an augmented set of training data for training an image generation model, wherein the augmented set of training data comprises a plurality of additional training examples, each additional training example corresponding to one of the training examples and comprising two images selected from the plurality of respective modified images generated for the corresponding training example.
What exactly they claim (claim 1)
1. A computer-implemented method comprising: obtaining a plurality of training examples, each training example comprising a respective first image depicting a corresponding scene when a target light source is in a first state and a respective second image depicting the corresponding scene when the target light source is in a second state; generating, for each training example, a plurality of respective modified images that each depict the corresponding scene when the target light source is in a respective modified state; and generating an augmented set of training data for training an image generation model, wherein the augmented set of training data comprises a plurality of additional training examples, each additional training example corresponding to one of the training examples and comprising two images selected from the plurality of respective modified images generated for the corresponding training example.
Facts
- Company
- Google (Google LLC)
- Official title
- GENERATING TRAINING DATA FOR GENERATING IMAGES WITH LIGHTING MODIFICATIONS
- Publication number
- US20260301382A1
- Application number
- 19569894
- Filed
- Mar 17, 2026
- Published
- Oct 1, 2026
- Inventors
- 6
- Claims
- 20
Classified under
G06V 10/774 Physics & computingG06T 11/60 Physics & computingMore from Google in AI & software
- Google patents video search that answers questions using AI descriptions Sep 15, 2026
- Google patents photo tool that removes people and their gear Sep 15, 2026
- Google patents AI that writes live meeting notes and summaries Sep 15, 2026
- Google patents AI tool that turns messy emergency notes into clear messages Sep 3, 2026
- Google patents AI that clicks through apps to finish tasks for you Sep 24, 2026
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.