US 11,688,038 B2
Apparatuses and methods for performing artificial intelligence encoding and artificial intelligence decoding on image
Jaehwan Kim, Suwon-si (KR); Jongseok Lee, Suwon-si (KR); Sunyoung Jeon, Suwon-si (KR); Kwangpyo Choi, Suwon-si (KR); Minseok Choi, Suwon-si (KR); Quockhanh Dinh, 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 Jan. 14, 2022, as Appl. No. 17/575,691.
Application 17/575,691 is a continuation of application No. 17/079,773, filed on Oct. 26, 2020, granted, now 11,288,770.
Application 17/079,773 is a continuation of application No. 16/656,812, filed on Oct. 18, 2019, granted, now 10,817,985, issued on Oct. 27, 2020.
Claims priority of application No. 10-2018-0125406 (KR), filed on Oct. 19, 2018; application No. 10-2019-0041108 (KR), filed on Apr. 8, 2019; and application No. 10-2019-0066057 (KR), filed on Jun. 4, 2019.
Prior Publication US 2022/0138904 A1, May 5, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 3/40 (2006.01); G06T 9/00 (2006.01); G06N 3/084 (2023.01); H04N 19/85 (2014.01); G06N 20/10 (2019.01)
CPC G06T 3/4046 (2013.01) [G06N 3/084 (2013.01); G06N 20/10 (2019.01); G06T 9/002 (2013.01); H04N 19/85 (2014.11); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 13 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
one or more processors configured to execute one or more instructions stored in the electronic device, to:
receive, from a server, AI data that is related to AI down-scaling an original image to a first image through a down-scaling neural network (NN) that operates according to first NN setting information, and an image data generated through an encoding on the first image, the first NN setting information being selected from a plurality of first NN setting information;
decode the image data to obtain a second image;
determine whether to perform AI up-scaling through an up-scaling NN, based on the AI data;
based on the AI up-scaling being determined to be performed:
select, based on the AI data, second NN setting information that is paired with the selected first NN setting information through joint training of the down-scaling NN and the up-scaling NN, from a plurality of second NN setting information that have one-to-one correspondence with the plurality of first NN setting information through the joint training;
obtain a third image corresponding to the original image by performing the AI up-scaling on the obtained second image through the up-scaling NN that operates according to the selected second NN setting information; and
provide, on the display of the electronic device, the obtained third image; and
based on the AI up-scaling of the obtained second image being determined to be not performed:
output the obtained second image.