US 11,816,872 B2
Method and apparatus for performing artificial intelligence encoding and artificial intelligence decoding
Chaeeun 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. 18, 2021, as Appl. No. 17/503,420.
Application 17/503,420 is a continuation of application No. 17/333,845, filed on May 28, 2021, granted, now 11,270,469.
Claims priority of application No. 10-2020-0070969 (KR), filed on Jun. 11, 2020; and application No. 10-2020-0128877 (KR), filed on Oct. 6, 2020.
Prior Publication US 2022/0036596 A1, Feb. 3, 2022
Int. Cl. G06T 9/00 (2006.01); G06N 3/08 (2023.01); G06T 3/40 (2006.01); G06V 10/44 (2022.01); G06V 10/82 (2022.01)
CPC G06T 9/002 (2013.01) [G06N 3/08 (2013.01); G06T 3/4046 (2013.01); G06V 10/454 (2022.01); G06V 10/82 (2022.01)] 5 Claims
OG exemplary drawing
 
1. An apparatus for performing artificial intelligence (AI) decoding on an image, the apparatus comprising:
a memory storing one or more instructions; and
at least one processor configured to execute the one or more instructions stored in the memory to:
obtain AI data and image data, the image data generated as a result of first encoding of a first image, and the AI data related to AI downscaling of an original image to the first image or AI one-to-one preprocessing of the original image 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, deep neural network (DNN) setting information for AI upscaling of the second image, from among a plurality of pieces of DNN setting information; and
generate a third image by performing the AI upscaling on the second image via an upscaling DNN operating based on the obtained DNN setting information,
wherein the plurality of pieces of DNN setting information are obtained via:
first joint training of the upscaling DNN and a downscaling DNN used for the AI downscaling of the original image, and
second joint training of a one-to-one preprocessing DNN used for the AI one-to-one preprocessing of the original image and the upscaling DNN, the second joint training being performed using DNN setting information for the AI upscaling obtained as a result of the first joint training.