Virtual-camera-based image acquisition method and related apparatus

Patent metadata

Field	Value
Publication number	US-2024303921-A1
Application number	US-202418667669-A
Country	US
Kind code	A1
Filing date	May 17, 2024
Priority date	Jul 22, 2022
Publication date	Sep 12, 2024
Grant date	—

Abstract

An image acquisition method includes importing a three-dimensional model of an object into a three-dimensional virtual photographing scene having a virtual world coordinate system, determining model position information and model attitude information of the three-dimensional model in the virtual world coordinate system, determining, according to a layout pattern of a plurality of virtual cameras in the three-dimensional virtual photographing scene, camera position information and camera attitude information of each of the plurality of virtual cameras in the virtual world coordinate system, and acquiring, for each of the plurality of virtual cameras, an image of the object from a viewing angle of the virtual camera according to the model position information, the model attitude information, the camera position information, and the camera attitude information.

First claim

What is claimed is:

1 . An image acquisition method comprising:
importing a three-dimensional model of an object into a three-dimensional virtual photographing scene having a virtual world coordinate system; determining model position information and model attitude information of the three-dimensional model in the virtual world coordinate system; determining, according to a layout pattern of a plurality of virtual cameras in the three-dimensional virtual photographing scene, camera position information and camera attitude information of each of the plurality of virtual cameras in the virtual world coordinate system; and acquiring, for each of the plurality of virtual cameras, an image of the object from a viewing angle of the virtual camera according to the model position information, the model attitude information, the camera position information, and the camera attitude information.

2 . The method according to claim 1 , wherein determining the camera position information and the camera attitude information of each of the plurality of virtual cameras in the virtual world coordinate system includes:
determining the camera position information according to the layout pattern; determining a position relationship between the three-dimensional model and the virtual camera according to the model position information and the camera position information; and performing attitude adjustment on the virtual camera according to the position relationship, to determine the camera attitude information.

3 . The method according to claim 1 , wherein acquiring, for each of the plurality of virtual cameras, the image of the object from the viewing angle of the virtual camera includes, for each virtual camera:
determining a distance between the three-dimensional model and the virtual camera according to the model position information, the model attitude information, the camera position information, and the camera attitude information; determining an extrinsic parameter of the virtual camera according to the camera position information and the camera attitude information; and acquiring the image according to the distance, the extrinsic parameter, and a preset intrinsic parameter of the virtual camera.

4 . The method according to claim 1 , further comprising:
determining the layout pattern, including:
obtaining layout configuration information of the plurality of virtual cameras in the three-dimensional virtual photographing scene; and
determining the layout pattern according to the layout configuration information.

5 . The method according to claim 1 , further comprising:
determining the layout pattern, including:
obtaining an initial layout pattern and layout adjustment information of the plurality of virtual cameras in the three-dimensional virtual photographing scene; and
determining the layout pattern according to the initial layout pattern and the layout adjustment information.

6 . The method according to claim 1 , wherein determining the model position information and the model attitude information of the three-dimensional model in the virtual world coordinate system includes:
obtaining position configuration information and attitude configuration information of the three-dimensional model in the virtual world coordinate system; and determining the model position information and the model attitude information according to the position configuration information and the attitude configuration information.

7 . The method according to claim 1 , wherein determining the model position information and the model attitude information of the three-dimensional model in the virtual world coordinate system includes:
obtaining initial model position information, initial model attitude information, and spatial transformation information of the three-dimensional model in the virtual world coordinate system; and determining the model position information and the model attitude information according to the initial model position information, the initial model attitude information, and the spatial transformation information.

8 . The method according to claim 7 , wherein:
the object includes a plurality of structure parts; the three-dimensional model includes a plurality of three-dimensional sub-models corresponding to the plurality of structure parts; and the spatial transformation information includes a plurality of pieces of spatial transformation sub-information corresponding to the plurality of three-dimensional sub-models.

9 . The method according to claim 1 , further comprising:
obtaining illumination configuration information of the three-dimensional virtual photographing scene; and determining an illumination condition of the three-dimensional virtual photographing scene according to the illumination configuration information; wherein acquiring, for each of the plurality of virtual cameras, the image of the object from the viewing angle of the virtual camera includes:
acquiring, for each virtual camera according to the model position information, the model attitude information, the camera position information, the camera attitude information, and the illumination condition, an image that satisfies the illumination condition.

10 . The method according to claim 1 , further comprising:
obtaining image attribute configuration information of the image; and determining image attribute information of the image according to the image attribute configuration information; wherein acquiring, for each of the plurality of virtual cameras, the image of the object from the viewing angle of the virtual camera includes:
acquiring, for each virtual camera according to the model position information, the model attitude information, the camera position information, the camera attitude information, and the image attribute information, an image that satisfies the image attribute information.

11 . The method according to claim 1 , further comprising:
obtaining background rendering information of the image; and rendering a preset background image of the image into a background image according to the background rendering information.

12 . A computer device comprising:
one or more processors; and one or more memories storing one or more computer programs that, when executed by the one or more processors, cause the one or more processors to:
import a three-dimensional model of an object into a three-dimensional virtual photographing scene having a virtual world coordinate system;
determine model position information and model attitude information of the three-dimensional model in the virtual world coordinate system;
determine, according to a layout pattern of a plurality of virtual cameras in the three-dimensional virtual photographing scene, camera position information and camera attitude information of each of the plurality of virtual cameras in the virtual world coordinate system; and
acquire, for each of the plurality of virtual cameras, an image of the object from a viewing angle of the virtual camera according to the model position information, the model attitude information, the camera position information, and the camera attitude information.

13 . The computer device according to claim 12 , wherein the one or more computer programs further cause the one or more processors to:
determine the camera position information according to the layout pattern; determine a position relationship between the three-dimensional model and the virtual camera according to the model position information and the camera position information; and perform attitude adjustment on the virtual camera according to the position relationsh

Assignees

• Tencent Tech Shenzhen Co Ltd

Inventors

• Xu Yiting
• Zhou Yi
• Yu Xiaoming
• Yi Yang
• Peng Chengwei
• Li Feng
• Zuo Xiaoxiang

Classifications

• G06T15/205

  Image-based rendering · CPC title

• G06T7/75 Primary

  involving models · CPC title

• G06T17/00 Primary

  Three-dimensional [3D] modelling for computer graphics · CPC title

• G06T15/20

  Perspective computation · CPC title

• G06T7/73 Primary

  using feature-based methods · CPC title