US 12,132,931 B2
Image encoding method and apparatus and image decoding method and apparatus using deep neural networks
Jongseok Lee, Suwon-si (KR); Youngo Park, Suwon-si (KR); Pilkyu Park, Suwon-si (KR); and Yumi Sohn, Suwon-si (KR)
Assigned to SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Gyeonggi-do (KR)
Filed on Jul. 28, 2022, as Appl. No. 17/876,043.
Application 17/876,043 is a continuation of application No. 17/081,364, filed on Oct. 27, 2020, granted, now 11,405,637, issued on Aug. 2, 2022.
Claims priority of application No. 10-2019-0135604 (KR), filed on Oct. 29, 2019.
Prior Publication US 2023/0074023 A1, Mar. 9, 2023
Int. Cl. H04N 19/59 (2014.01); G06N 3/04 (2023.01); G06T 3/4046 (2024.01); H04N 19/172 (2014.01); H04N 19/61 (2014.01)
CPC H04N 19/59 (2014.11) [G06N 3/04 (2013.01); G06T 3/4046 (2013.01); H04N 19/172 (2014.11); H04N 19/61 (2014.11)] 17 Claims
OG exemplary drawing
 
10. A display apparatus for decoding an image, comprising:
a processor configured to:
receive, from a server, an image data generated through an encoding of a first image that has been down-scaled by a down-scaling neural network (NN), and artificial intelligence (AI) data related to an update of NN setting information;
based on NN update indication information indicating that NN setting information of an up-scaling NN is updated, obtain updated NN setting information of the up-scaling NN based on NN update information;
obtain a second image by decoding the image data;
obtain a third image by up-scaling the second image using an updated up-scaling NN that has been updated based on the updated NN setting information; and
provide, on a display, the obtained third image,
wherein, based on the NN update indication information indicating that the NN setting information is not updated, the third image is obtained by up-scaling the second image using an up-scaling NN set with first NN setting information that is pre-stored in the display apparatus.