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 get edge labels for PCN and Completion3d #1

Open
GitBoSun opened this issue Oct 27, 2021 · 4 comments
Open

How to get edge labels for PCN and Completion3d #1

GitBoSun opened this issue Oct 27, 2021 · 4 comments

Comments

@GitBoSun
Copy link

Hi, thanks for sharing your great work here. When I tried loading the PCN dataset, I found the edge label is required in the dataset but i couldn't find how to compute it. When I loaded 'our dataset', there's no category and model name (e.g. 03001627/123b44b99e48eccb6960dc525de2f934) corresponding to shapenet. Could you please provide the name list of your dataset?

@xiaogangw
Copy link
Owner

Hi, thanks for your interest in our work. Since the PCN dataset is very big, we did not upload their edges, but the edges can be easily obtained. The edge label generation algorithm is illustrated in our supplementary. I will also upload the edge label generation code later.
As to "our dataset" , the name list is different with PCN dataset but same with ShapeNetPart dataset in PointNet++.

@Fayeben
Copy link

Fayeben commented Feb 25, 2022

Hi, thanks a lot for your work. Could you please provide the edge generation code for study. Many thanks!!!

@Marigod98
Copy link

Hi, thanks a lot for your work. Could you please provide the edge ground truth generation code for study. Many thanks!!!

@xiaogangw
Copy link
Owner

@Fayeben @Marigod98 Thanks for your interest in our work and sorry for the late reply. I have updated the code to generate edge points in edge_detection.py, feel free to have a try.

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