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

How to convert the .ply file of the PCN dataset into a .pcd file #2

Open
LiRui64 opened this issue Mar 26, 2023 · 5 comments
Open

How to convert the .ply file of the PCN dataset into a .pcd file #2

LiRui64 opened this issue Mar 26, 2023 · 5 comments

Comments

@LiRui64
Copy link

LiRui64 commented Mar 26, 2023

How to convert the .ply file of the PCN dataset into a .pcd file.Because when doing seh training, the input requirement of sest.py is a .pcd file, but after the PCN dataset is downloaded, it is a .ply file

@Chen-Albert-FENG
Copy link
Member

Open your terminal, then "pcl_ply2pcd -h xxx.ply xxx.pcd" to convert ply to pcd using pcl lib.

@KerouacDlg
Copy link

There are multiple ply files with the same name, such as xxx_1.ply, xxx_2.ply, xxx_3.ply. If they are directly converted into pcd files, the SPM module still cannot read them.

@KerouacDlg
Copy link

But there are files with the same name inside such as xx_1.ply, xx_2.ply, xx_3.ply, etc. How should I deal with them?

@mode-str
Copy link

mode-str commented Dec 26, 2023

But there are files with the same name inside such as xx_1.ply, xx_2.ply, xx_3.ply, etc. How should I deal with them?

I'm having the same problem as you. Have you solved this problem? Besides, I would like to know how the data is organized. If you can give me some information, I would appreciate it.

@KerouacDlg
Copy link

KerouacDlg commented Dec 28, 2023

This is how I handled it. I copied multiple copies of the point cloud files in the complete folder and named them xxx_1.pcd, xxx_2.pcd.... Let them correspond to the files in the partial folder. Then modify the contents in the .list file。

But the problem I encountered when processing the house3k data set is that after processing the data set, the first dimension of many pillars is zero, which I cannot solve.
image

image

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

4 participants