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.

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：US20240185454A1

公开(公告)日：2024-06-06

申请号：US18551738

申请日：2022-04-12

Applicant: Beijing Zitiao Network Technology Co., Ltd.

Inventor： Liyou XU ,  Jinyuan WU

IPC: G06T7/73 ,  G06T7/50 ,  G06T13/00

CPC classification number: G06T7/73 ,  G06T7/50 ,  G06T13/00 ,  G06T2210/21 ,  G06T2210/56

Abstract: The embodiments of the present disclosure provide a particle rendering method and apparatus, which relate to the technical field of image rendering. The method includes: obtaining state information of a target particle; obtaining a fall duration of the target particle if the state information is first state information indicating that no collision with the target particle occurred; obtaining a first position based on the fall duration and a fall speed of the target particle; and rendering the target particle to be at the first position.

公开(公告)号：US20240005573A1

公开(公告)日：2024-01-04

申请号：US18357651

申请日：2023-07-24

Applicant: BEIJING ZITIAO NETWORK TECHNOLOGY CO., LTD.

Inventor： Liyou XU ,  Chenxiang ZHAO

IPC: G06T11/20 ,  G06T7/90 ,  G06V10/56 ,  G06V10/75

CPC classification number: G06T11/203 ,  G06T7/90 ,  G06V10/56 ,  G06V10/751 ,  G06T2207/10024

Abstract: A method for generating a signed distance field image, methods for processing a text effect, a device and a medium are provided. The method for generating a signed distance field image includes: determining a target closed curve in an unsigned distance field image of target text, and drawing a target triangle; performing counting for pixels within the target triangle based on a drawing direction of the target triangle; determining that pixels having counting results equal to 0 in the unsigned distance field image are located in an interior region of the target text, and determining that pixels having counting results not equal to 0 in the unsigned distance field image are located in the exterior region of the target text; and generating a signed distance field image of the target text based on the pixels located in the exterior region of the target text, the pixels located in the interior region of the target text, and the unsigned distance field image.