公开(公告)号：US20250124636A1

公开(公告)日：2025-04-17

申请号：US18999813

申请日：2024-12-23

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Peibin CHEN ,  Xijin ZHANG ,  Fuxing LENG

IPC: G06T13/40 ,  G06T17/00 ,  G06V40/16

Abstract: Embodiments of the present disclosure relate to an expression driving method and apparatus, a device, and a medium. The method includes: obtaining a target image, and recognizing an expression of a target object in the target image to obtain at least one expression coefficient; extracting an expression coefficient to be processed from the at least one expression coefficient, and determining an initial left expression coefficient and an initial right expression coefficient in the expression coefficient to be processed; generating a target left expression coefficient and a target right expression coefficient based on a similarity between the initial left expression coefficient and the initial right expression coefficient; and driving a virtual character to show a corresponding expression based on the target left expression coefficient and the target right expression coefficient.

公开(公告)号：US20240290137A1

公开(公告)日：2024-08-29

申请号：US18692767

申请日：2022-09-13

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Jingna SUN ,  Peibin CHEN ,  Yueming LV

IPC: G06V40/16 ,  G06T11/60

CPC classification number: G06V40/168 ,  G06T11/60

Abstract: A face image processing method and apparatus, and a device and a medium are provided. The method includes: acquiring a first feature map and a second feature map of a current layer, and generating a plurality of original makeup feature regions corresponding to a plurality of face parts according to the first feature map, generating a plurality of reference makeup feature regions corresponding to the plurality of face parts according to the second feature map, performing makeup migration calculation on each of the original makeup feature regions and a corresponding reference makeup feature region to acquire a plurality of candidate makeup feature regions, stitching the plurality of candidate makeup feature regions to generate a target feature map, and judging whether the target feature map satisfies a preset decoding condition.