US 11,810,265 B2
Image reconstruction method and device, apparatus, and non-transitory computer-readable storage medium
Dehui Kong, Shenzhen (CN); Ke Xu, Shenzhen (CN); Xiao Zhang, Shenzhen (CN); Bin Han, Shenzhen (CN); Zhou Han, Shenzhen (CN); Hong Wang, Shenzhen (CN); Guoning Lu, Shenzhen (GD); Long Huang, Shenzhen (CN); and Sheng Luo, Shenzhen (CN)
Assigned to SANECHIPS TECHNOLOGY CO., LTD., Shenzhen (CN)
Appl. No. 17/299,557
Filed by SANECHIPS TECHNOLOGY CO., LTD., Shenzhen (CN)
PCT Filed Dec. 20, 2019, PCT No. PCT/CN2019/126859
§ 371(c)(1), (2) Date Jun. 3, 2021,
PCT Pub. No. WO2020/125740, PCT Pub. Date Jun. 25, 2020.
Claims priority of application No. 201811565875.0 (CN), filed on Dec. 20, 2018.
Prior Publication US 2022/0036506 A1, Feb. 3, 2022
Int. Cl. G06T 3/40 (2006.01); G06T 5/50 (2006.01); G06F 18/25 (2023.01)
CPC G06T 3/4007 (2013.01) [G06F 18/251 (2023.01); G06T 5/50 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 13 Claims
OG exemplary drawing
 
1. An image reconstruction method, comprising:
determining norms of convolution kernels of each convolutional layer of a deep neural network model;
determining the convolution kernels with norms greater than or equal to a preset threshold in each convolutional layer to obtain a target convolution kernel set of each convolutional layer, wherein the target convolution kernel set of each convolutional layer comprises the convolution kernels with norms greater than or equal to the preset threshold;
processing an input image of each convolutional layer by using the convolution kernels in the target convolution kernel set of each convolutional layer respectively, to obtain a first image processing result for the deep neural network model;
obtaining a second image processing result by performing interpolation on an initial image; and
determining a fusion result according to the first image processing result and the second image processing result and reconstructing the initial image according to the fusion result;
wherein processing an input image of each convolutional layer by using the convolution kernels in the target convolution kernel set of each convolutional layer respectively comprises:
processing the input image by using the convolution kernels with norms greater than or equal to the preset threshold in response to a difference between a maximum norm and a minimum norm of the convolution kernels in the target convolution kernel set of each convolutional layer respectively being within a preset range; and
sorting the convolution kernels in a descending order of the norms in response to the difference between the maximum norm and minimum norm of the convolution kernels in the target convolution kernel set of each convolutional layer respectively not being within the preset range, and processing the input image by using first M convolution kernels in a sorting result, wherein M is a natural number greater than or equal to 1.