	US 12,256,179 B2
	Color reconstruction using homogeneous neural network
Yotam Ater, Tel-Aviv (IL); Heejin Choi, Tel-Aviv (IL); Natan Bibelnik, Tel-Aviv (IL); Woo-shik Kim, Tel-Aviv (IL); Evgeny Soloveichik, Tel-Aviv (IL); and Ortal Glatt, Tel-Aviv (IL)
Assigned to SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed on Nov. 14, 2022, as Appl. No. 18/055,098.
Prior Publication US 2024/0163410 A1, May 16, 2024
Int. Cl. H04N 9/67 (2023.01); G06N 3/048 (2023.01); H04N 9/64 (2023.01); H04N 23/84 (2023.01); H04N 25/13 (2023.01); H04N 25/131 (2023.01)

CPC H04N 9/67 (2013.01) [G06N 3/048 (2023.01); H04N 9/646 (2013.01); H04N 23/843 (2023.01); H04N 25/131 (2023.01); H04N 25/135 (2023.01)]

19 Claims

1. A method for image processing, comprising:

receiving image sensor data from an image sensor of a camera device;

applying a non-linear color space mapping to the image sensor data using a neural network to obtain image data, wherein the non-linear color space mapping comprises a non-negative homogeneous function; and

storing the image data in a memory of the camera device.