US 11,810,332 B2
Apparatus and method for performing artificial intelligence (AI) encoding and AI decoding on image
Jongseok Lee, Suwon-si (KR); Jaehwan Kim, Suwon-si (KR); and Youngo Park, Suwon-si (KR)
Assigned to SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed on Oct. 6, 2021, as Appl. No. 17/495,050.
Application 17/495,050 is a continuation of application No. 17/180,358, filed on Feb. 19, 2021, granted, now 11,164,340.
Application 17/180,358 is a continuation of application No. 17/082,442, filed on Oct. 28, 2020, granted, now 11,610,341.
Claims priority of application No. 10-2019-0134514 (KR), filed on Oct. 28, 2019.
Prior Publication US 2022/0028121 A1, Jan. 27, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 9/00 (2006.01); G06N 3/08 (2023.01); G06T 3/40 (2006.01); G06N 3/082 (2023.01)
CPC G06T 9/002 (2013.01) [G06N 3/082 (2013.01); G06T 3/4046 (2013.01)] 16 Claims
OG exemplary drawing
 
1. An electronic device for displaying an image by using an artificial intelligence (AI), the electronic device comprising:
a display; and
at least one processor configured to execute one or more instructions to:
obtain image data generated from performing first encoding on a first image and AI data related to AI down-scaling of at least one original image related to the first image;
obtain a second image corresponding to the first image by performing first decoding on the image data;
obtain, based on the AI data, neural network (NN) setting information for performing AI up-scaling of the second image;
identify whether to perform the AI up-scaling by using a filter kernel of a convolution layer in a predetermined NN or whether to perform the AI up-scaling by using a filter kernel of a convolution layer in a NN updated for performing the AI up-scaling of at least one second image corresponding to at least one original image via a joint training of an up-scaling NN and a down-scaling NN used for the AI down-scaling of the at least one original image, the joint training being performed using the at least original image; and
generate a third image by performing the AI up-scaling on the second image via the up-scaling NN operating according to the NN setting information based on the identifying.