US 11,720,997 B2
Artificial intelligence (AI) encoding device and operating method thereof and AI decoding device and operating method thereof
Minseok Choi, Suwon-si (KR); Kwangpyo Choi, Suwon-si (KR); and Jaehwan Kim, Suwon-si (KR)
Assigned to SAMSUNG ELECTRONICS CO.. LTD., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed on Oct. 11, 2019, as Appl. No. 16/599,291.
Claims priority of application No. 10-2018-0125406 (KR), filed on Oct. 19, 2018; application No. 10-2018-0138298 (KR), filed on Nov. 12, 2018; application No. 10-2019-0041099 (KR), filed on Apr. 8, 2019; and application No. 10-2019-0078343 (KR), filed on Jun. 28, 2019.
Prior Publication US 2020/0126185 A1, Apr. 23, 2020
Int. Cl. G06T 3/40 (2006.01); H04N 19/42 (2014.01); H04N 19/33 (2014.01); G06N 3/02 (2006.01); H04N 19/85 (2014.01)
CPC G06T 3/4046 (2013.01) [G06N 3/02 (2013.01); H04N 19/33 (2014.11); H04N 19/42 (2014.11); H04N 19/85 (2014.11)] 17 Claims
OG exemplary drawing
 
1. An artificial intelligence (AI) decoding apparatus comprising:
a display;
a memory storing one or more instructions; and
a processor configured to execute the stored one or more instructions to:
obtain AI data related to AI downscaling an original image to a first image, and image data corresponding to an encoding result on the first image, the AI data comprising an index indicating neural network (NN) setting information for an AI upscaling;
obtain a second image by decoding the obtained image data;
select a first NN setting information from a plurality of first NN setting information based on the AI data, the first NN setting information being for performing the AI upscaling on the obtained second image;
obtain a third image that is upscaled from the second image, by performing an operation between the second image and first parameters of a filter kernel comprised in an upscaling NN set with the selected first NN setting information;
providing the third image on the display,
wherein each of the first parameters is represented by a product of a scale factor and one among integer values, and each of the integer values is 0 or ±2n, where n is an integer,
wherein the first image is obtained based on a downscaling NN set with a selected second NN setting information from among a plurality of second NN setting information for the AI downscaling,
wherein the plurality of first NN setting information and the plurality of second NN setting information are obtained through joint training of the downscaling NN and the upscaling NN,
wherein the first parameters are set in association with second parameters of a filter kernel comprised in the downscaling NN, and
wherein the AI data includes information indicating a target of the AI upscaling including a target resolution.