pyntcloud and torch-points3d
These are complements: pyntcloud provides general-purpose point cloud data loading and preprocessing utilities, while torch-points3d builds on PyTorch to apply deep learning models to those processed point clouds.
About pyntcloud
daavoo/pyntcloud
pyntcloud is a Python library for working with 3D point clouds.
About torch-points3d
torch-points3d/torch-points3d
Pytorch framework for doing deep learning on point clouds.
Provides modular implementations of 13+ state-of-the-art architectures (PointNet++, KPConv, MinkowskiEngine, etc.) organized by task—classification, segmentation, registration, detection, and panoptic analysis. Leverages PyTorch Geometric for graph operations and Hydra for configuration-driven training, enabling reproducible experiments across benchmark datasets with minimal boilerplate. Includes sparse convolution backends and a high-level API for rapid prototyping of complex point cloud models.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work