公开(公告)号：US20250148957A1

公开(公告)日：2025-05-08

申请号：US19005481

申请日：2024-12-30

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jonghwan KIM ,  Seonseok KIM ,  Guiwon SEO ,  Chun ZHAO

IPC: G09G3/20 ,  G06T5/92

Abstract: A display device including: a display; and at least one processor connected to the display and configured to control the display device, where the at least one processor is configured to: identify an input image as a plurality of areas, identify a type of each of the plurality of areas by identifying at least one of the plurality of areas as a focus area and by identifying other areas of the plurality of areas as a background area, obtain a global tone mapping curve (TMC) for the input image based on a pixel level reduction amount corresponding to a target power consumption reduction amount, allocate a power consumption reduction amount to each of the plurality of areas based on the type of each of the plurality of areas, obtain a local tone mapping curve for each of the plurality of areas.

公开(公告)号：US20250166369A1

公开(公告)日：2025-05-22

申请号：US19025126

申请日：2025-01-16

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Chun ZHAO ,  Seonseok KIM ,  Jonghwan KIM ,  Guiwon SEO

IPC: G06V10/70 ,  G06V10/82

Abstract: An electronic device is configured to identify a scene type of a first frame included in a content by inputting the first frame into the first neural network model, transmit the scene type of the first frame to a server, receive, from the server in response to the transmitted scene type of the first frame, a second neural network model and a first parameter corresponding to the scene type of the first frame, replace the first neural network model with the second neural network model, and perform image processing on the first frame based on the first parameter, and in which the second neural network model is one of a plurality of second neural network models respectively corresponding to a plurality of scene types that can be output from the first neural network model.