pytorch-pointcloud

A PyTorch library for deep learning on point clouds: models, pretrained weights, datasets, transforms and inferers, inspired by timm.

Check out the official docs at pytorch-pointcloud.org!

Object classification pointnet2-ssg.modelnet40.xu-yan	Part segmentation pointnext-sm.shapenetpart.openpoints	Indoor segmentation / detection ptv3-base.scannet20.pointcept
Outdoor segmentation / detection spvcnn-119gmacs.semantickitti.mit-han-lab second.kitti.openpcdet	Large scale segmentation utonia-lp.scannet20.pointcept	Feature extraction sonata-lp.scannet20.fair

Installation

Install the library with pip (or uv):

pip install torch-pointcloud

Quickstart

import torch
import torch_pointcloud as tp

# Requires torch-cluster, torch-scatter
model = tp.create_model(
    "pointnext-sm.scanobjectnn.openpoints",
    task="classification",
    pretrained=True,
).eval()

pos = torch.randn(2048, 3)  # (N, 3) coordinates
x = torch.cat([pos, pos[:, 1:2] - pos[:, 1].min()], dim=1)  # (N, 4) features: xyz + height
batch = torch.zeros(2048, dtype=torch.long)  # (N,) batch index

with torch.no_grad():
    logits = model(x, pos, batch)  # (1, 15)

Every checkpoint ships the transform that turns a raw point cloud into what the network expects:

# Requires torch-scatter, torch-cluster, spconv
model, info = tp.create_model("ptv3-base.scannet20.pointcept", task="segmentation", pretrained=True, return_info=True)
info["transform"]  # the preprocessing pipeline of that checkpoint
info["weights"]["metrics"]  # {"mIoU": 77.40}

tp.list_models("pointnext*")  # every registered PointNeXt config
tp.list_models(task="detection", pretrained=True)  # all detection checkpoints

See the examples directory for benchmarks and training recipes.

Documentation

The documentation covers installation, a get-started guide, the model zoo, datasets, transforms, tutorials and the full API reference.

Citation

If you find this project useful, please consider citing:

@software{dujardin2026pytorchpointcloud,
  author = {Dujardin, Arthur},
  title = {PyTorch PointCloud},
  year = {2026},
  url = {https://github.com/arthurdjn/pytorch-pointcloud},
  doi = {10.5281/zenodo.22159633},
  license = {Apache-2.0}
}

License

Apache 2.0. See LICENSE.