公开(公告)号：US20230317117A1

公开(公告)日：2023-10-05

申请号：US18331340

申请日：2023-06-08

Applicant: BEIJING ZITIAO NETWORK TECHNOLOGY CO., LTD.

Inventor： Junqiang WANG ,  Ziyang ZHENG ,  Weihong GUAN ,  Haitao LV ,  Wanling LIN ,  Jiali YE ,  Weiwen LIN ,  Yang LI ,  Zhanchen ZHANG ,  Yingwen ZENG ,  Xin CHE

IPC: G11B27/036 ,  H04N21/4788

CPC classification number: G11B27/036 ,  H04N21/4788

Abstract: A video generation method includes: when a video theme configured by a user and a video production instruction are obtained, obtaining, according to the video production instruction, a user image and multiple video templates matching the video theme; embedding the user image into reserved positions of at least some of the video templates so that the user image is combined with situational materials of the video templates to generate at least one video; obtaining a video to be published from the at least one video, and publishing the video to be published to a preset video playback platform. Thus, during the process of video production, at least one video can be generated at a time as long as the user image is embedded into multiple video templates, without repeatedly photographing by a user.

公开(公告)号：US20230133416A1

公开(公告)日：2023-05-04

申请号：US18089377

申请日：2022-12-27

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Xinjing YE ,  Junsheng WU ,  Haitao LV ,  Xi GAO

IPC: G11B27/031 ,  G06T7/20 ,  G06T7/70

Abstract: An image processing method and apparatus, and a device and a medium are provided. The image processing method comprises: determining a motion state of a first recognition object in an initial video image; determining a motion state of a material object according to the motion state of the first recognition object; if the motion state of the material object is a first state, synthesizing the material object and a first-style video image according to the motion state of the material object, to obtain a first target video image; and if the motion state of the material object is a second state, synthesizing the material object and a second-style video image according to the motion state of the material object, to obtain a second target video image. The first-style video image and the second-style video image are images of different styles obtained from the initial video image.