Alexandre Boulch

This paper is about classification and semantic segmentation.

Hello, The code for data preparation should be the one from [PointCNN](https://github.com/yangyanli/PointCNN/). You could try with this code. It should generate the same npy.

Hello, The code was not tested on Windows. I am not familiar with missing dependencies on this platform. Let me know if you find a solution, it may benefit to...

Hello, Sorry for late response, is your question still valid ? Part of the computation is done on CPU (nearest neighbor search essentially), it could be due to cpu/memory lagging.

Hello, Sorry for this very late response. Yes, in order to import lightconvpoint.knn, you need to import torch first. This is something that will be changed.

Hello, Sorry for very late response. - What is EMA ? - We select the points randomly in each voxel, the whole selection process for quantized sampling is not purely...

Hello, Thanks for the issue. I am planning to release a version without C++ module compilation by the end of the month (March). Like that, it should rely only on...

Hello, No in this repo, we only reimplemented the network architecture of KPConv for K-nearest neighbors conv. layers, not the convolutional layer described in KPConv.

Hello, You cannot do for now. I have coded only the spatial search using K-nearest neighbors (all search algorithm are based on KNN not radius). I do not know if...

Hello, Thank you for pointing the error. I commented the call to dataset.dfaust. I shall add the DFaust dataset file as soon as I have cleaned the code for release.