US 12,423,820 B2
Image segmentation method and apparatus, computer device, and storage medium
Shuang Yu, Shenzhen (CN); Wei Ji, Shenzhen (CN); Kai Ma, Shenzhen (CN); and Yefeng Zheng, Shenzhen (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed by TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed on Dec. 5, 2022, as Appl. No. 18/074,906.
Application 18/074,906 is a continuation of application No. PCT/CN2022/077951, filed on Feb. 25, 2022.
Claims priority of application No. 202110234267.7 (CN), filed on Mar. 3, 2021.
Prior Publication US 2023/0106468 A1, Apr. 6, 2023
Int. Cl. G06T 7/00 (2017.01); G06T 7/10 (2017.01)
CPC G06T 7/10 (2017.01) [G06T 2207/20084 (2013.01); G06T 2207/20221 (2013.01); G06T 2207/20224 (2013.01)] 20 Claims
OG exemplary drawing
 
1. An image segmentation method, performed by a computer device, the method comprising:
encoding an original image based on a prior knowledge vector, to obtain a target feature map, the original image comprising a target object, the prior knowledge vector comprising a plurality of prior knowledge weights, each of the prior knowledge weights representing accuracy of a corresponding rater labeling a region of an object in an image;
decoding the target feature map, to obtain a first segmented image of the original image, the first segmented image indicating a target region in which the target object is located in the original image;
performing image reconstruction on the first segmented image based on the prior knowledge vector, to obtain a plurality of labeled segmented images, wherein one labeled segmented image corresponds to one prior knowledge weight and indicates a target region labeled by a corresponding rater; and
processing the target feature map based on the plurality of labeled segmented images, to obtain a second segmented image of the original image.