US 12,190,471 B2
Image processing apparatus and operating method thereof
Sangwook Baek, Suwon-si (KR); Sangwon Lee, Suwon-si (KR); Taekeun Kang, Suwon-si (KR); Dongkyu Kim, Suwon-si (KR); Gihyeon Bae, Suwon-si (KR); Jungmin Lee, Suwon-si (KR); Youngo Park, Suwon-si (KR); and Kwangpyo Choi, Suwon-si (KR)
Assigned to SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed on Apr. 18, 2022, as Appl. No. 17/723,055.
Application 17/723,055 is a continuation of application No. PCT/KR2022/004156, filed on Mar. 24, 2022.
Claims priority of application No. 10-2021-0101025 (KR), filed on Jul. 30, 2021; and application No. 10-2021-0176998 (KR), filed on Dec. 10, 2021.
Prior Publication US 2023/0031143 A1, Feb. 2, 2023
Int. Cl. G06T 3/4046 (2024.01); G06T 3/4007 (2024.01); G06T 7/00 (2017.01)
CPC G06T 3/4046 (2013.01) [G06T 3/4007 (2013.01); G06T 7/0002 (2013.01)] 15 Claims
OG exemplary drawing
 
1. An image processing apparatus for performing image quality processing on an image, the image processing apparatus comprising:
a memory configured to store one or more instructions; and
a processor configured to execute the one or more instructions stored in the memory to:
obtain a first image by downscaling an input image, by using a downscale network comprising at least one downscale block;
extract first feature information corresponding to the first image, by using a feature extraction network comprising at least one feature extraction block;
obtain a second image by performing image quality processing on the first image based on the first feature information, by using an image quality processing network comprising at least one modulation block; and
obtain an output image by upscaling the second image and performing image quality processing on the upscaled second image, by using an upscale network, the upscale network comprising at least one upscale block and at least one spade block,
wherein the processor is further configured to execute the one or more instructions to:
by using the at least one spade block, extract second feature information corresponding to the input image and perform image quality processing on the upscaled second image based on the second feature information.