Pointnet++ Part segmentation

This repo is implementation for PointNet++ part segmentation model based on PyTorch and pytorch_geometric.

The model has been mergered into pytorch_geometric as a point cloud segmentation example, you can try it.

Performance

Segmentation on A subset of shapenet.

Note,

• mcIOU: mean per-class pIoU
• The model uses single-scale grouping with raw points as input.
• All experiments are trained with same default configration: npoints=2500, batchsize=8, num_epoches=30. The recorded accuracy above is the test accuracy of the final epoch.

Requirements

• PyTorch
• pytorch_geometric
• Open3D(optional, for visualization of segmentation result)

Quickly install pytorch_geometric and Open3D with Anaconda

$ pip install --verbose --no-cache-dir torch-scatter
$ pip install --verbose --no-cache-dir torch-sparse
$ pip install --verbose --no-cache-dir torch-cluster
$ pip install --verbose --no-cache-dir torch-spline-conv (optional)
$ pip install torch-geometric

# optional
conda install -c open3d-admin open3d

Usage

Training

python main.py

Show segmentation result

python vis/show_seg_res.py

Sample segmentation result

Links

• pointnet.pytorch by fxia22. This repo's tranining code is heavily borrowed from fxia22's repo.
• Official PointNet and PointNet++ tensorflow implementations
• PointNet++ classification example of pytorch_geometric library