Method, system and computing device for reconstructing three-dimensional planes

Abstract

A method, a system, and a computing device for reconstructing three-dimensional planes are provided. The method includes the following steps: obtaining a series of color information, depth information and pose information of a dynamic scene by a sensing device; extracting a plurality of feature points according to the color information and the depth information, and marking part of the feature points as non-planar objects including dynamic objects and fragmentary objects; computing point cloud according to the unmarked feature points and the pose information, and instantly converting the point cloud to a three-dimensional mesh; and growing the three-dimensional mesh to fill vacancy corresponding to the non-planar objects according to the information of the three-dimensional mesh surrounding or adjacent to the non-planar objects.

Description

technical field [0001] The invention relates to a three-dimensional plane reconstruction method, a three-dimensional plane reconstruction system and a computing device. Background technique [0002] Generally, a mobile camera module scans the scene to establish a three-dimensional scene model. However, when scanning the scene, there are often people walking around, and the correct 3D scene model cannot be reconstructed. [0003] In many applications, only the planar structure in a 3D scene needs to be reconstructed, without including cluttered small objects or people. [0004] The amount of point cloud data generated by scanning the scene with the general method is very large, and it is necessary to obtain all the point clouds before converting them into meshes. This will occupy a large amount of memory and processor resources, and cannot be effectively applied to the headset. [0005] Therefore, researchers are devoting themselves to developing a new technology for scanni...

AI Technical Summary

Problems solved by technology

[0004] The amount of point cloud data generated by scanning the scene with the general method is very large, and it is necessary to obtain all the point clouds before converting them into grids. This will take up a lot of memory and processor resources and cannot be effectively applied to head-mounted devices.

Images