Samsung Patent Granted for Image Processing

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published March 24th, 2026

Detected March 25th, 2026

Summary

The USPTO has granted Samsung Electronics Co., Ltd. a patent for an electronic device and method for image processing through a canonical space. The patent, application number 18324635, was filed on May 26, 2023, and granted on March 24, 2026.

View original document View source feed page

What changed

The United States Patent and Trademark Office (USPTO) has granted Samsung Electronics Co., Ltd. patent US12586343B2 for an electronic device and method related to image processing through a canonical space. The patent details a process involving training images from a first sensor, converting them to correspond to a second sensor's output, and further converting color values to train a generative model for canonical space images. This patent was filed under application number 18324635 on May 26, 2023, and officially granted on March 24, 2026.

This patent grant is primarily an intellectual property matter and does not impose new regulatory obligations on other entities. However, companies operating in the AI, image processing, and electronic device manufacturing sectors, particularly those developing similar technologies, should be aware of Samsung's patented innovations. The grant of this patent may influence future product development and licensing strategies within the industry.

Source document (simplified)

← USPTO Patent Grants

Electronic device and method with image processing through canonical space

Grant US12586343B2 Kind: B2 Mar 24, 2026

Assignee

Samsung Electronics Co., Ltd.

Inventors

Junsang Yu, Dong Young Kim, Seon Joo Kim, Kinam Kwon

Abstract

Provided are an electronic devices and methods for processing an image through a canonical space, the method including receiving training images of a scene obtained from a first sensor, generating first conversion images by converting the training images into images corresponding to a scene obtained through a second sensor, generating second conversion images by converting a color value of the training images and a color value of the first conversion images, and training a canonical image generative model configured to convert the training images, the first conversion images, and the second conversion images into canonical space images of a canonical color space and a canonical illumination space.