公开(公告)号：US20230290043A1

公开(公告)日：2023-09-14

申请号：US18198172

申请日：2023-05-16

申请人： Tencent Technology (Shenzhen) Company Limited

发明人： Wensheng CAO ,  Wei Cao ,  Tangxi Chen ,  Xiaojie Wang ,  Lijun Yuan ,  Chong Zhang ,  Meng Zhai ,  Xingyuan Zhu

IPC分类号： G06T15/20 ,  G06T15/50

CPC分类号： G06T15/20 ,  G06T15/503

摘要： Disclosed are a picture generation method performed by a computer device. The method includes: rendering a three-dimensional virtual scene to obtain a scene background rendering map; rendering a first foreground target reported by a first terminal associated with a first client to obtain a first foreground target rendering map; blending the scene background rendering map and the first foreground target rendering map to obtain a first picture, the first picture including the first foreground target displayed in the three-dimensional virtual scene; and providing the first picture to the first terminal associated with the first client for displaying the first picture. A technology of thousand people with thousand faces is achieved, the rendering efficiency can be improved, and the cost is saved.

公开(公告)号：US12087069B2

公开(公告)日：2024-09-10

申请号：US17516585

申请日：2021-11-01

申请人： TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

发明人： Wanchao Chi ,  Chong Zhang ,  Yonggen Ling ,  Wei Liu ,  Zhengyou Zhang ,  Zejian Yuan ,  Ziyang Song ,  Ziyi Yin

IPC分类号： G06K9/00 ,  G06N3/045 ,  G06V30/242 ,  G06V40/20

CPC分类号： G06V30/242 ,  G06N3/045 ,  G06V40/20

摘要： An artificial intelligence-based action recognition method includes: determining, according to video data comprising an interactive object, node sequence information corresponding to video frames in the video data, the node sequence information of each video frame including position information of nodes in a node sequence, the nodes in the node sequence being nodes of the interactive object that are moved to implement a corresponding interactive action; determining action categories corresponding to the video frames in the video data, including: determining, according to the node sequence information corresponding to N consecutive video frames in the video data, action categories respectively corresponding to the N consecutive video frames; and determining, according to the action categories corresponding to the video frames in the video data, a target interactive action made by the interactive object in the video data.