US 11,741,581 B2
Training method for image processing model, image processing method, network device, and storage medium
Hongyun Gao, Shenzhen (CN); Xin Tao, Shenzhen (CN); Jiaya Jia, Shenzhen (CN); Yuwing Tai, Shenzhen (CN); and Xiaoyong Shen, Shenzhen (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed by TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed on May 27, 2021, as Appl. No. 17/332,970.
Application 17/332,970 is a continuation of application No. PCT/CN2020/077699, filed on Mar. 4, 2020.
Claims priority of application No. 201910259016.7 (CN), filed on Apr. 1, 2019.
Prior Publication US 2021/0287047 A1, Sep. 16, 2021
Int. Cl. G06K 9/00 (2022.01); G06T 5/00 (2006.01); G06T 3/40 (2006.01); G06T 5/50 (2006.01); G06V 10/94 (2022.01); G06F 18/214 (2023.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01)
CPC G06T 5/003 (2013.01) [G06F 18/2148 (2023.01); G06T 3/4046 (2013.01); G06T 5/50 (2013.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 10/95 (2022.01); G06T 2207/20016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A training method for an image processing model for processing blurry images, performed by a network device, the image processing model comprising a first network and a second network; the first network and the second network being codec networks with different scales; the sizes of the scales corresponding to the measurements of the sharpness of to-be-processed blurry images; and the method comprising:
obtaining a sample pair for training, the sample pair comprising a clear image and a blurry image corresponding to the clear image; and the sharpness of the clear image being greater than a preset threshold, and the sharpness of the blurry image being less than the preset threshold;
activating the image processing model to perform sharpness restoration on the blurry image to obtain a restored image; and
updating network parameters of the first network and network parameters of the second network in the image processing model according to the restored image and the clear image to obtain a trained image processing model;
wherein the network parameters of the first network and the network parameters of the second network meet a selective sharing condition, and the selective sharing condition indicates the network parameters between the first network and the second network are shared or independent.