erikwijmans/Pointnet2_PyTorch

Health v2 · maintenance only

Adoption not part of the score

1812 stars · 399 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A PyTorch implementation of Pointnet2/Pointnet++ for deep learning on point clouds, including custom CUDA ops for GPU-only execution. It supports multi-GPU training and example classification and semantic segmentation training scripts built with PyTorch Lightning and Hydra.

Use cases

• train pointnet++ models in pytorch
• classify 3d point clouds with deep learning
• semantic segmentation of point clouds
• run pointnet2 cuda ops in pytorch
• multi-gpu training of point cloud networks

When to choose

• you need a PyTorch port of Pointnet++ with CUDA ops
• you want reference implementations of classification or semantic segmentation on point clouds
• you are pinned to older PyTorch versions (1.4/1.5) where this was tested

When to avoid

• you need maintained code or issue support - the project is explicitly unmaintained
• you lack a CUDA GPU - custom ops are GPU-only
• you need recent PyTorch compatibility - it was tested only up to PyTorch 1.5

Facets

library · maturity abandoned

machine-learning deep-learning machine-learning computer-vision python point-cloud pointnet2 pytorch cuda-ops semantic-segmentation point-cloud-classification gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="erikwijmans/Pointnet2_PyTorch")