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 keypoints in intermediate files? #10

Closed
yokinglou opened this issue Oct 20, 2021 · 4 comments
Closed

How to get keypoints in intermediate files? #10

yokinglou opened this issue Oct 20, 2021 · 4 comments

Comments

@yokinglou
Copy link

Thanks for your implementation of PPF-FoldNet.

I am curious about how to generate the keypoints in intermediate files. Are these keypoints generated by your algorithms or provided by 3DMatch?

Best,
Yoking

@XuyangBai
Copy link
Owner

XuyangBai commented Oct 20, 2021

Hi, I am not sure whether you are asking the keypoint for training or not. But as you can see here, I choose randomly selected point as keypoint for training

def select_referenced_point(pcd, num_patches=2048):
# A point sampling algorithm for 3d matching of irregular geometries.
pts = np.asarray(pcd.points)
num_points = pts.shape[0]
inds = np.random.choice(range(num_points), num_patches, replace=False)

For testing, 3DMatch do provide keypoints which are also randomly generated.

@yokinglou
Copy link
Author

Thanks for your reply. I ask keypoints that used for geometric registration task, since you provide a link to download the intermediate files which include the keypoints for registration. Are these keypoints provided by 3DMatch and generated randomly (like you said for testing)?

@XuyangBai
Copy link
Owner

They are provided by 3DMatch and I think also generated randomly ...

See https://vision.princeton.edu/projects/2016/3DMatch/#geometric-registration-benchmark

image

@yokinglou
Copy link
Author

Get it. Thanks.

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