公开(公告)号：US20240193804A1

公开(公告)日：2024-06-13

申请号：US18022455

申请日：2022-11-03

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Siyuan WANG ,  Yitong LI ,  Liyou XU

IPC: G06T7/73 ,  G06T7/33

CPC classification number: G06T7/73 ,  G06T7/33 ,  G06T2207/20044 ,  G06T2207/30196

Abstract: Provided are an image processing method and apparatus, an electronic device, and a storage medium. The method includes determining a to-be-registered skeleton chain and a preset skeleton chain of a target part in a to-be-processed video frame; determining wrist or ankle state information of the to-be-registered wrist or ankle skeleton point according to first pose information of the to-be-registered wrist or ankle skeleton point and second pose information of the preset wrist or ankle skeleton point; determining finger or toe state information of the to-be-registered finger or toe skeleton point according to the wrist or ankle state information, third pose information of the to-be-registered finger or toe skeleton point, and fourth pose information of the preset finger or toe skeleton point; and displaying the target part in the to-be-processed video frame according to the wrist or ankle state information and the finger or toe state information.

公开(公告)号：US20240378784A1

公开(公告)日：2024-11-14

申请号：US18027865

申请日：2022-11-03

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Liyou XU ,  Siyuan WANG

IPC: G06T13/40 ,  G06T7/50 ,  G06T7/60 ,  G06T19/00

Abstract: Provided are an image processing method and apparatus, an electronic device, and a storage medium. The method includes dividing a target virtual subject in a to-be-processed video frame into multiple skeleton chains, where each of the multiple skeleton chains includes at least one skeleton point; determining collision information between at least one skeleton point in the multiple skeleton chains and a colliding body and determining target display information of the at least one skeleton point in the to-be-processed video frame according to the collision information; and controlling the target virtual subject to be displayed in the to-be-processed video frame according to the target display information of the at least one skeleton point.