Pointnet_Pointnet2_pytorch icon indicating copy to clipboard operation
Pointnet_Pointnet2_pytorch copied to clipboard

Published 20 hours ago • verified publisher icon yanx27

Question regarding Dataloaders for Semantic Segmentation using PointNet++

Open An-u-rag opened this issue 2 years ago • 1 comments

Hi, I am slightly confused about a couple of things.

  1. Why are there two separate dataloaders for train_semseg and test_semseg in S3DISDataLoader.py? Both seem to use different techniques for subsampling of points.
  2. I am confused regarding the concept of hierarchical partitioning of input point clouds, there seems to be a sampling done in the dataloaders as well as the PointNetAbstraction layers. However, The PointNet++ paper only mentions furthest point sampling and a volumetric ball query around it. Why is that?
  3. The S3DISDataset seems to use a random sampling technique to get blocks of fixed number of points whereas ScannetDatasetWholeScene uses grid sampling to get a block of fixed number of points. Why is this done? Would this not give inaccurate results?

An-u-rag avatar Mar 19 '23 22:03 An-u-rag

Any update on this?

FSet89 avatar Mar 05 '24 15:03 FSet89