	US 12,229,881 B2
	Method and apparatus for generating three-dimensional face model, computer device, and storage medium
Wenpan Li, Shenzhen (CN); Linchao Bao, Shenzhen (CN); and Xiangkai Lin, Shenzhen (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed by TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed on Mar. 29, 2022, as Appl. No. 17/707,937.
Application 17/707,937 is a continuation of application No. PCT/CN2020/125386, filed on Oct. 30, 2020.
Claims priority of application No. 202010049667.6 (CN), filed on Jan. 16, 2020.
Prior Publication US 2022/0222893 A1, Jul. 14, 2022
Int. Cl. G06T 17/00 (2006.01); G06T 3/60 (2024.01); G06T 7/40 (2017.01); G06T 7/55 (2017.01); G06T 7/70 (2017.01); G06V 10/22 (2022.01); G06V 10/56 (2022.01); G06V 10/764 (2022.01); G06V 40/16 (2022.01); G06V 40/18 (2022.01)

CPC G06T 17/00 (2013.01) [G06T 3/60 (2013.01); G06T 7/40 (2013.01); G06T 7/55 (2017.01); G06T 7/70 (2017.01); G06V 10/225 (2022.01); G06V 10/56 (2022.01); G06V 10/764 (2022.01); G06V 40/168 (2022.01); G06V 40/172 (2022.01); G06V 40/174 (2022.01); G06V 40/18 (2022.01); G06T 2200/08 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/10024 (2013.01); G06T 2207/10028 (2013.01); G06T 2207/20221 (2013.01); G06T 2207/30201 (2013.01); G06T 2207/30208 (2013.01); G06T 2210/56 (2013.01)]

16 Claims

1. A method for generating a three-dimensional face model, applied to a computer device, the method comprising:

obtaining a plurality of target face images, comprising:

obtaining a plurality of face images that comprise a same face;

classifying the plurality of face images according to image types of the plurality of face images, to obtain a plurality of image sequences, each image sequence comprising face images of a same image type, wherein the image type comprises a front face type, a left face type, a right face type, or a head-up type, the plurality of image sequences comprise at least a first image sequence corresponding to the front face type and at least a second image sequences corresponding to an other image type;

selecting a first face image from the first image sequence as one of the target face images;

obtaining posture angle differences between second face images in each second image sequence and the first face image; and

selecting, among the second face images in one second image sequence based on the posture angle differences, a second face image with a largest posture angle difference as one of the target face images;

obtaining a plurality of depth images corresponding to the plurality of target face images, the plurality of depth images comprising depth information corresponding to pixels in the target face images;

obtaining, according to an image type of each target face image, a regional face image that is in each target face image and that corresponds to the image type of each target face image;

obtaining a regional depth image in a corresponding depth image according to the regional face image; and

performing image fusion based on the plurality of obtained regional face images and the plurality of obtained regional depth images, to generate a three-dimensional face model.