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
about farthest point sampling #83
Comments
Hi, |
Can you please provide screenshots or something? Also note that FPS algorithm used in PointNet++ is a) approximate (point zero is always included in the output set) and b) greedy, meaning that it is completely liable to make some errors. |
You can get the test data from this .zip file, including a mesh model.obj, a point cloud model.pcd. test code:
|
Can you try removing these two lines: https://github.com/erikwijmans/Pointnet2_PyTorch/blob/master/pointnet2_ops_lib/pointnet2_ops/_ext-src/src/sampling_gpu.cu#L100-L101 I filtered out near-zero points to avoid some numerical instabilities, but, if a model is very small, that may cause issue. |
Thanks, this issue fixed. |
Sounds good. I will consider removing that or making the limit tighter. IIRC, the instability was due to my specific down-stream application at the time. |
hi, @erikwijmans Thank you for the quality code. I have few questions.
And yours seems pretty fast. (same condition, 1024 points to 512 points, etc) |
Hi, authors,
The Farthest Point Sampling (FPS) is applied in the official implementation of pointnet2. However, I could not find FPS implementation in your package? Does your package provide FPS function?
THX!
The text was updated successfully, but these errors were encountered: