search

XuyangBai / PPF-FoldNet

PyTorch reimplementation for "PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors" https://arxiv.org/abs/1808.10322
99 stars 19 forks source link

How to get keypoints in intermediate files? #10

Closed yokinglou closed 3 years ago

yokinglou commented 3 years ago

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 commented 3 years ago

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 https://github.com/XuyangBai/PPF-FoldNet/blob/63af940632ad2350141e332314aab99f41766378/input_preparation.py#L52-L56 For testing, 3DMatch do provide keypoints which are also randomly generated.

yokinglou commented 3 years ago

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 commented 3 years ago

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

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

image

yokinglou commented 3 years ago

Get it. Thanks.