Serialization / Hilbert ordering.

[karannb]

Hello does the current code-base have code for imposing a specific order and then serializing it? If no, will you be uploading it? If yes, I can't find it; in fact I think

choice = np.random.choice(len(seg), self.npoints, replace=True)
# resample
point_set = point_set[choice, :]
seg = seg[choice]

at line 155 in ./part_segmentation/dataset.py effectively randomizes the order of the points (which I guess might work, but is not what the paper reports).

Thank you!

[LMD0311]

Thank you for your interest in our work! We have recently updated the paper introducing a scanning strategy based on space-filling curves and made minor adjustments to the network architecture to improve performance. The related code will be updated soon, so stay tuned.

Regarding the code you mentioned, in fact the random ordering of each point in the point cloud is a routine operation, this is because the point cloud is permutation invariant, i.e. the order of swapping still represents the same 3D object. On the other hand, we scan FPS-sampled key points along a space-filling curve, which differs from the random ordering.

[karannb]

Sure! can you please close this issue with the release I guess? So I know when to pull the changes. Thanks.

[LL-C8]

@karannb
Hi, I encountered the same issue. Have you resolved it? If so, could you please share your code?
Thank you！

[karannb]

@LL-C8, no I have not solved it, I believe there are a few open source libraries for ordering point clouds, but I am waiting for the authors to release it.

However, you can work with the ShapeNet Part dataset which on my run was within < 0.5% than their reported number with the special ordering.