TL;DR该论文提出了解决点集配准问题的一种新方法,名为 GOGMA,它利用 SE(3)空间的几何特征,采用分支限界的方法来搜索 3D 刚性运动的空间,从而保证全局最优解,同时还能加速收敛,而且经过实验证明该方法比现有的全局最优解方法具有更强的鲁棒性。
Abstract
gaussian mixture alignment is a family of approaches that are frequently used
for robustly solving the point-set registration problem. However, since they
use local optimisation, they are susceptible to local min