Explaination of compute_fpfh_features

[MartinPedersenpp]

Checklist

• [X] I have searched for similar issues.
• [X] For Python issues, I have tested with the latest development wheel.
• [X] I have checked the release documentation and the latest documentation (for master branch).

My Question

I have tried reading the paper and looked at the source code behind the compute_fpfh_features function, but I can't seem to find the link between the papers explanation of the function and the implementation in o3d. Where does the 33 dimensions come from in regards to finding KNN points pr. each point in the point cloud?

I might have overlooked something, but a broad explanation of the implementation would be appreciated.

EDIT: I noticed that for each point in the point cloud, the sum of the 33 dimensions always end at 600, I can't find anything about this in the source code.

[halil-karabacak]

Hi, I also have the same question. Have you find any resources on this? Thanks