Multi-view Registration Based on Weighted Low Rank and Sparse Matrix Decomposition of Motions

Congcong Jin, Jihua Zhu, Yaochen Li, Shanmin Pang, Lei Chen, Jun Wang

Published 2017-09-25Version 1

Recently, the low rank and sparse (LRS) matrix decomposition has been introduced as an effective mean to solve the multi-view registration. However, this method presents two notable disadvantages: the registration result is quite sensitive to the sparsity of the LRS matrix; besides, the decomposition process treats each block element equally in spite of their reliability. Therefore, this paper firstly proposes a matrix completion method based on the overlap percentage of scan pairs. By completing the LRS matrix with reliable block elements as much as possible, more synchronization constraints of relative motions can be utilized for registration. Furthermore, it is observed that the reliability of each element in the LRS matrix can be weighed by the relationship between its corresponding model and data shapes. Therefore, a weight matrix is designed to measure the contribution of each element to decomposition and accordingly, the decomposition result is closer to the ground truth than before. Benefited from the more informative LRS matrix as well as the weight matrix, experimental results conducted on several public datasets demonstrate the superiority of the proposed approach over other methods on both accuracy and robustness.