	US 12,277,747 B2
	Method and apparatus for image processing and image synthesis for obtaining a target face image, and computer-readable storage medium
Xiaoyi Li, Shenzhen (CN); and Mengren Qian, Shenzhen (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed by Tencent Technology (Shenzhen) Company Limited, Shenzhen (CN)
Filed on Jun. 8, 2022, as Appl. No. 17/835,817.
Application 17/835,817 is a continuation of application No. PCT/CN2021/088641, filed on Apr. 21, 2021.
Claims priority of application No. 202010486646.0 (CN), filed on Jun. 1, 2020.
Prior Publication US 2022/0301284 A1, Sep. 22, 2022
Int. Cl. G06T 7/73 (2017.01); G06T 7/50 (2017.01); G06T 7/62 (2017.01); G06V 10/22 (2022.01); G06V 10/40 (2022.01); G06V 10/75 (2022.01); G06V 10/80 (2022.01); G06V 40/18 (2022.01)

CPC G06V 10/757 (2022.01) [G06T 7/50 (2017.01); G06T 7/62 (2017.01); G06T 7/74 (2017.01); G06V 10/22 (2022.01); G06V 10/40 (2022.01); G06V 10/7515 (2022.01); G06V 10/806 (2022.01); G06V 40/193 (2022.01); G06T 2207/10012 (2013.01); G06T 2207/20068 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20221 (2013.01); G06T 2207/30201 (2013.01)]

20 Claims

1. An image processing method performed by a computer device, the method comprising:

performing feature point recognition on a face image to obtain a plurality of facial feature points of the face image;

determining feature point position offset information between the plurality of facial feature points and a plurality of reference facial feature points of a reference face image;

performing, based on the feature point position offset information, position adjustment on a facial feature point of a reference face depth image to obtain a target face depth image corresponding to the face image, the reference face depth image being a face depth image corresponding to the reference face image; and

performing direction deflection on the face image according to the target face depth image to obtain a target face image.