PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.

3D point cloud datasets in HDF5 format, containing uniformly sampled 2048 points per shape.

3D DenseNet(torch version) for ModelNet40 dataset

This is the official repository of the original Point Transformer architecture.

similar data search for 3D voxel data

Basic reference for Multi View Classification - mvcnn

Parses OFF (Object File Format) 3D model files to a class container. Includes helper functions for downloading and parsing publicly available datasets.

3D point cloud data augmentation