Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

精度问题请教 #55

Open
chenxiaocongAI opened this issue Jul 16, 2024 · 2 comments
Open

精度问题请教 #55

chenxiaocongAI opened this issue Jul 16, 2024 · 2 comments

Comments

@chenxiaocongAI
Copy link

chenxiaocongAI commented Jul 16, 2024

问题: BALM2的精度为什么比BALM1高。
我的理解:BALM 1在构建cost fuction利用了所有的feature的点云,而BALM2.0在点云的基础上做了聚类,改变了costfuction,利用的local map的约束应该没有所有的点云多,理论上计算时间的确会比BALM1低,但这精度在理论上怎么去分析?
理论上costfuction没怎么改变,只不过BALM2.0改变了costfuction形式,使其计算速度加快,但理论上约束基本没有大变化,精度这么大提升是什么原因呢

@Zale-Liu
Copy link
Member

如果BALM1.0能用上所有的点,那么两者精度的确是一样的。不过如果用上所有点,时间会花费非常非常长,因此一般都会对点云进行降采样,而BALM2.0可以使用所有点的信息,因此BALM1.0的精度在实际数据集中会不如2.0高

@chenxiaocongAI
Copy link
Author

chenxiaocongAI commented Aug 20, 2024 via email

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants