SamsungGranted patentAI & softwareInterest 6/10

Samsung patents AI method to sharpen photos by treating near and far objects differently

Patent drawing
Patent drawing from the official filing.

Samsung describes a method that uses three separate neural networks to improve the quality of low-resolution images. One network identifies whether objects are close or far, while two others specifically enhance those areas, and a final step blends the results into a single sharper picture.

Why it mattersThis technique could help cameras produce clearer photos by applying different sharpening rules to the foreground and background, which is a common challenge in smartphone photography.

In the filing’s own words

Provided are an image processing method and an input processing device based on a neural network, the method including: obtaining a feature map distinguishing between a near object and a distant object of a low-resolution input image, obtaining a composited weight map for the low-resolution input image by inputting the feature map to a first Deep Neural Network (DNN), obtaining a first image by inputting the low-resolution input image to a second DNN suitable for restoring a distant object, obtaining a second image by inputting the low-resolution input image to a third DNN suitable for restoring a near object, and obtaining a high-resolution image for the low-resolution input image by performing weighted averaging on the first image and the second image using the composited weight map.

What exactly they claim (claim 1)

1. An image processing method based on a neural network, the image processing method comprising: obtaining a feature map distinguishing between a near object and a distant object of a low-resolution input image; obtaining a composited weight map for the low-resolution input image by inputting the feature map to a first Deep Neural Network (DNN); obtaining a first image by inputting the low-resolution input image to a second DNN trained to restore the distant object in the low-resolution input image; obtaining a second image by inputting the low-resolution input image to a third DNN trained to restore the near object in the low-resolution input image; and obtaining a high-resolution image corresponding to the low-resolution input image by performing weighted averaging on the first image and the second image using the composited weight map.

Facts

Company
Samsung (Samsung Electronics Co., Ltd.)
Official title
Image processing method and image processing device based on neural network
Patent number
US12802175B2
Application number
18616953
Filed
Mar 26, 2024
Granted
Nov 17, 2026
Inventors
8
Claims
17

Classified under

G06T 5/60 Physics & computingG06T 5/50 Physics & computingG06T 2207/20016 Physics & computingG06T 2207/20084 Physics & computingG06T 2207/20216 Physics & computing

More from Samsung 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.