Samsung patents AI camera system that adjusts brightness and image features
Samsung describes a method where a camera captures a raw image and sends it to a specific AI model to adjust brightness levels. A second AI model then analyzes the adjusted image to extract features, which a third AI model refines based on user settings to create the final photo.
In the filing’s own words
A device and a method for generating an output image in which a subject has been captured are provided. A method of performing image processing may include: obtaining a raw image by a camera sensor of the device, by using a first processor configured to control the device; inputting the raw image to a first artificial intelligence (AI) model trained to scale image brightness, by using a second processor configured to perform AI-based image processing on the raw image; obtaining tone map data output from the first AI model, by using the second processor; and storing an output image generated based on the tone map data.
What exactly they claim (claim 1)
1. A method of performing image processing by a device, the method comprising: obtaining a raw image by controlling a camera sensor of the device, by using a first processor configured to control the device; inputting the raw image to a first artificial intelligence (AI) model trained to scale image brightness, by using a second processor configured to perform AI-based image processing on the raw image; obtaining tone map data output from the first AI model, by using the second processor; obtaining tone-modified image data by applying the tone map data to the raw image; extracting image features from the tone-modified image data by inputting the tone-modified image data into a second AI model; obtaining modified image features from a third AI model by inputting the image features and at least one of setting values related to image attributes into the third AI model; and generating an output image based on the modified images features.
Facts
- Company
- Samsung (SAMSUNG ELECTRONICS CO., LTD.)
- Official title
- Device and method for generating image in which subject has been captured
- Patent number
- US12770235B2
- Application number
- 18131643
- Filed
- Apr 6, 2023
- Granted
- Oct 20, 2026
- Inventors
- 4
- Claims
- 17
Classified under
G06T 5/92 Physics & computingG06V 10/44 Physics & computingG06V 10/56 Physics & computingG06V 10/60 Physics & computingH04N 1/6077 Electricity & electronicsG06T 2207/10024 Physics & computingMore from Samsung in AI & software
- Samsung patents tool to erase objects from photos using AI Sep 24, 2026
- Samsung patents drawing objects into photos with AI Oct 15, 2026
- Samsung patents AI that creates personalized exercise videos Sep 10, 2026
- Samsung patents AI summaries for paused TV shows based on your viewing habits Sep 24, 2026
- Samsung patents turning chat conversations into image prompts Oct 1, 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.