Jiacheng Liu

@HuguesTHOMAS Thanks for your reply!!! I also think I should find my own solution to this problem! And thanks for your time!! I really appreciate it!!! Well another question: Could...

@HuguesTHOMAS Hello Thomas！It is me still.. Could this Net work on the dataset which only has XYZ and true_class values(without RGB features compared withS3DIS)?

@HuguesTHOMAS Thank you for your reply and this wonderful work, that is really cool !!! But why the parameter "in_features_dim" should be modified from 5 to 1, in the S3DIS...

@HuguesTHOMAS Thanks for your reply! Well the s3dis.py line736 else: print('\nPreparing KDTree for cloud {:s}, subsampled at {:.3f}'.format(cloud_name, dl)) # Read ply file data = read_ply(file_path) points = np.vstack((data['x'], data['y'],...

Hello! @HuguesTHOMAS - I have been troubled by these problems recently and hope to your guidance. I found that the original_ply data will be grid_subsampled twice before being fed into...

> I personally do not use the code on windows, so I am afraid I won't be of much help. This repo is aimed at Linux primarily, if you want...

> > have you considered adding a weak supervision module to the kpconv framework? > > No, this repo is really for defining a 3D point cloud convolution. It should...