Question on the method of KNN query.

[Youngju-Na]

Hi! Thanks for the great work.
How does the KNN work so fast in the implementation?

In the paper, you said that you query K neighboring neural points around it within a certain radius R.
However, I'm uncertain where I can find this inside the code.
I would be happy if you let me know some details of how KNNs on huge point clouds are done so fast and implementation details.

Thanks!