Determination method and device for three-dimensional modeling and electronic equipment

CN120689525APending Publication Date: 2025-09-23CHINA UNITED NETWORK COMM GRP CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202511006379.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-07-21
Publication Date
2025-09-23

AI Technical Summary

Technical Problem

Traditional 3D modeling methods have problems such as high training consumption for full-scene modeling, long modeling time, and inaccurate 2D semantic segmentation, resulting in low modeling efficiency and poor accuracy.

Method used

By obtaining the shooting position parameters of the preset camera, the bounding box of the target object and the rendered depth map, the farthest depth parameter set is determined, the target mask is used to accurately mark the modeling area, and multiple two-dimensional images are combined for three-dimensional modeling to optimize the modeling process.

Benefits of technology

It improves the accuracy and efficiency of 3D modeling, reduces the cost of modeling training, and improves the integrity and accuracy of modeling.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120689525A_ABST
    Figure CN120689525A_ABST
Patent Text Reader

Abstract

The invention discloses a three-dimensional modeling determination method and device and electronic equipment, relates to the technical field of three-dimensional modeling, and aims to solve the problem of how to accurately carry out three-dimensional modeling on a target object. The method comprises the following steps: acquiring a shooting position parameter of a preset camera, a bounding box of a target object, a rendering depth map of the target object and a plurality of two-dimensional images of the target object; determining a farthest depth parameter set based on shooting position parameters of a preset camera and a bounding box of the target object; determining a target mask based on the farthest depth parameter set and the rendering depth map of the target object; and determining a three-dimensional model of the target object based on the plurality of two-dimensional images and the target mask. Three-dimensional modeling can be accurately carried out on the target object, so that the modeling training consumption is reduced, and the modeling efficiency is improved.
Need to check novelty before this filing date? Find Prior Art