3D Reconstruction Based on Dense Point Cloud Sampling and Filtering Optimization Algorithm

Abstract

In order to solve the problems of large memory consumption and large reconstruction error in the process of dense point cloud 3D reconstruction, an optimal reconstruction method of dense point cloud sampling and filtering is proposed. First of all, the feature points are extracted and matched, the mismatching is removed, the camera pose is calculated, and the sparse point cloud is generated. Then, the sparse point cloud is densified, and the improved sampling algorithm and filtering algorithm are used to reduce the memory and optimize the dense point cloud. Finally, the optimized dense point cloud is reconstructed and smoothed. The experimental results show that after the sampling algorithm, the computational memory required in the reconstruction process decreases from 5.3GB to 3.2GB, and the relative error of the optimized point cloud reconstruction is less than 4%, which is significantly lower than that before optimization. By comparison, it is found that the relative error is reduced by 1% to 3%. Experimental results verify the effectiveness of the method and show that the dense point cloud reconstruction with higher accuracy can be achieved with lower computational memory.