@【面特征】【参数化放入g2o】带有更高维特征的图优化SLAM平面表达

We tackle the problem of plugging planes into the g2o optimization framework with two distinct plane representations: one based on a properly stated SE(3) parametrization and one based on a minimal parametrization analogous to quaternions.

评价好坏的标准为Absolute Trajectory Error (ATE) and Relative Pose Error (RPE)

整个文章架构是问题的优化模型建模，不同李代数和四元数的平面表达方式，对于未来工作的展望是如何加入前端，平面的检测，如何matching(2016年)