A distributed optimization method for large-scale grids

Abstract

The invention discloses a distributed optimization large-scale mesh method, which distributively optimizes the initial mesh after mesh reconstruction in three-dimensional reconstruction. The method comprises the following steps: (1) dividing the input initial mesh into a plurality of mesh blocks and sending the mesh blocks to each machine of the cluster; (2) adding boundary constraints on each machine of that clust to distributively simplify and refine the mesh blocks obtained in the step 1); (3) sending the mesh blocks processed in the step (2) on each machine to the master of the cluster, fusing the mesh blocks, and simplifying and refining the mesh blocks to obtain a uniform mesh with no redundant vertices; (4) using multi-layer K-path segmentation algorithm, the aerial images of UAV being segmented into K sub-images; (5) utilizing the image set obtained in the step (4) to distributively restore the detail features of the mesh obtained in the step (3). The invention can generate a smooth mesh with rich detail features from the input initial mesh.

Description

technical field [0001] The invention belongs to the field of computer virtual reality, in particular, a method for optimizing a large-scale grid based on distribution. It is mainly used in the fields of film and television animation, virtual reality and surveying and mapping. Background technique [0002] In recent years, unmanned aerial vehicles (UAVs) have gradually attracted people's attention. The aerial images captured by UAVs have the advantages of large scale, wide viewing angle, and high potential. Combining with oblique photography technology, it is easy to obtain high-quality, Image of a large outdoor static scene with rich textures. Combining UAV aerial images with 3D reconstruction of sequential images, it is of great application value to carry out related research on 3D reconstruction of outdoor scenes. This research can establish an efficient, convenient, and relatively cheap 3D reconstruction system for large-scale outdoor scenes, which will play an importan...

AI Technical Summary

Problems solved by technology

[0003] At present, many researchers have conducted a lot of research on the various steps of 3D reconstruction. Recently, Vu et al. used optical flow consistency to optimize the grid and restore the detailed features of the grid. However, this method consumes too much memory, and Running time is too slow to be applied to large-scale meshes

There are no relevant literature reports on large-scale grid optimization

Images