EnyaHermite/SPH3D-GCN

Ruemonge

Jihao-Li opened this issue · 2 comments

Jihao-Li commented

Thank you for your code. I have some questions about Ruemonge dataset.

  1. I download this dataset, but I didn't find the 'pcl.txt' file. This is in SPH3D-GCN/preprocesing/ruemonge2014_prepare_data.m line 13 data = load('pcl.txt');.
  2. According to your paper, point clouds are splie into blocks. When I load the _pcl split.mat_file, some blocks contains less than 8192 point clouds. What did you deal with it? Repeat sampling?
    Lookinf forward to your reply!
EnyaHermite commented
  1. I think the 'pcl.txt' file should be the transformed format of the 'pcl.ply' file in the dataset.
  2. Yes. Your guess is correct. Check lines 329-332 in train_ruemonge2014.py for the sampling strategy.
atomishcv commented

@JihaoLee Can you give the download link of the RueMonge2014 dataset