US 12,444,058 B2
Facial image processing method and apparatus, device, and storage medium
Feida Zhu, Shenzhen (CN); Junwei Zhu, Shenzhen (CN); Yun Cao, Shenzhen (CN); Ying Tai, Shenzhen (CN); Chengjie Wang, Shenzhen (CN); and Jilin Li, Shenzhen (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed by TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed on May 10, 2023, as Appl. No. 18/315,065.
Application 18/315,065 is a continuation of application No. PCT/CN2022/103392, filed on Jul. 1, 2022.
Claims priority of application No. 202110913421.3 (CN), filed on Aug. 10, 2021.
Prior Publication US 2023/0281833 A1, Sep. 7, 2023
Int. Cl. G06T 7/246 (2017.01); G06V 10/77 (2022.01); G06V 10/774 (2022.01); G06V 20/40 (2022.01); G06V 40/16 (2022.01)
CPC G06T 7/246 (2017.01) [G06V 10/7715 (2022.01); G06V 10/774 (2022.01); G06V 20/40 (2022.01); G06V 40/174 (2022.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30201 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A facial image processing method, performed by a computer device and comprising:
obtaining first optical flow information, the first optical flow information representing offsets of a plurality of key points of a target object in a first facial sample image and a second facial sample image;
obtaining, based on the first optical flow information, second optical flow information through an optical flow information prediction sub-model of an image processing model, the second optical flow information representing offsets between a plurality of pixels in the first facial sample image and a plurality of corresponding pixels in the second facial sample image;
generating, based on the first facial sample image and the second optical flow information, a predicted image of the first facial sample image through a generator of the image processing model;
discriminating the predicted image and the second facial sample image through a discriminator of the image processing model to obtain a first discrimination result and a second discrimination result, the first discrimination result indicating whether the predicted image is a true sample image, and the second discrimination result indicating whether the second facial sample image is a true sample image; and
training the image processing model based on the first discrimination result, the second discrimination result, the predicted image, the second facial sample image, the first optical flow information, and the second optical flow information.