US 11,967,045 B2
Image processing device and method
Zikun Liu, Beijing (CN); Chunying Li, Beijing (CN); Han Qiu, Beijing (CN); and Yinglu Liu, Beijing (CN)
Assigned to Samsung Electronics Co., Ltd, (KR)
Appl. No. 17/272,866
Filed by SAMSUNG ELECTRONICS CO., LTD., Gyeonggi-do (KR)
PCT Filed Sep. 6, 2019, PCT No. PCT/KR2019/011557
§ 371(c)(1), (2) Date Mar. 2, 2021,
PCT Pub. No. WO2020/050686, PCT Pub. Date Mar. 12, 2020.
Claims priority of application No. 201811049734.3 (CN), filed on Sep. 7, 2018.
Prior Publication US 2021/0192687 A1, Jun. 24, 2021
Int. Cl. G06T 3/4053 (2024.01); G06N 3/08 (2023.01); G06T 3/4046 (2024.01)
CPC G06T 3/4053 (2013.01) [G06N 3/08 (2013.01); G06T 3/4046 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An image processing method comprises:
obtaining an input image;
converting the input image or a feature map of the input image into a plurality of target input images or target feature maps, wherein a resolution of each of the target input images or the target feature maps is smaller than a resolution of the feature map of the input image or the input image, and pixels at the same position in each of the target input images or the target feature maps are of a neighborhood relationship with the input image or the feature map of the input image;
processing at least a part of the plurality of target input images or target feature maps by one or more convolution blocks in a convolutional neural network; and
increasing a resolution of a feature map output from the one or more convolution blocks in the convolutional neural network,
wherein processing the at least the part of the plurality of target input images or target feature maps by the one or more convolution blocks in the convolutional neural network comprises convoluting the at least the part of the plurality of target input images or target feature maps according to information differences of the plurality of target input images or the target feature mas.