Samsung patents AI method to fix blurry spots in edited photos
This patent describes a method for improving images after a user edits them, such as removing an object. It uses an AI model to compare small sections of the image to find matching textures, then fills in missing details to make the result look natural.
In the filing’s own words
Methods and apparatuses for performing image processing using artificial intelligence are provided. In an embodiment, an image processing method includes acquiring a target image based on an editing operation on an original image, performing a filling processing operation on the target image to obtain a first filled image including a first target region, identifying a target patch based on the first filled image, calculating a similarity value between the target patch and at least one patch related to the first filled image using a first artificial intelligence (AI) model, determining a target residual patch corresponding to the target patch based on the similarity value and generating a processing result image based on the target residual patch.
What exactly they claim (claim 1)
1. An image processing method, comprising: acquiring a target image based on an editing operation on an original image, wherein the target image comprises an unknown region formed by the editing operation; performing a filling processing operation on the target image to obtain a filled image comprising a target region, wherein the target region corresponds to the unknown region; identifying a target image patch comprising at least a portion of the target region in the filled image; tiling the target image patch to generate a tile image with a predetermined third size comprising a plurality of tiles corresponding to the target image patch; obtaining a similarity value between the target image patch and at least one image patch from the filled image by inputting the tile image into a first artificial intelligence (AI) model; determining a residual patch associated with an image patch among the at least one image patch as a target residual patch associated with the target image patch based on the similarity value, wherein the residual patch comprises high frequency texture information associated with the image patch; and generating a processing result image based on the target residual patch and the filled image.
Facts
- Company
- Samsung (SAMSUNG ELECTRONICS CO., LTD.)
- Official title
- Image processing method and related device
- Patent number
- US12743752B2
- Application number
- 18074003
- Filed
- Dec 2, 2022
- Granted
- Sep 22, 2026
- Inventors
- 7
- Claims
- 20
Classified under
G06T 5/77 Physics & computingG06T 3/4046 Physics & computingG06T 7/74 Physics & computingG06T 11/40 Physics & computingG06V 10/761 Physics & computingG06V 10/7715 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.