charlesq34/pointnet2

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

3700 stars · 931 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Official TensorFlow implementation of PointNet++, a deep neural network that learns hierarchical features on 3D point clouds using metric-space locality. It includes classification and segmentation models, custom TF ops, and training/testing/visualization utilities.

Use cases

• classify 3D point clouds with deep learning
• semantic segmentation of point clouds from LiDAR or depth sensors
• learn hierarchical features on 3D shapes
• reproduce the PointNet++ NIPS'17 paper results
• benchmark point cloud models on ModelNet and ShapeNet
• build custom point cloud models with set abstraction layers

When to choose

• you need the reference implementation of PointNet++ for research or reproduction
• you work with 3D point cloud classification or segmentation in TensorFlow 1.x
• you want a well-cited baseline for point cloud deep learning

When to avoid

• you need modern PyTorch or TensorFlow 2.x support
• you want a maintained production-ready library rather than research code
• you need point cloud models with recent architectures or active community support

Facets

library · maturity maintenance

deep-learning machine-learning computer-vision computer-vision deep-learning machine-learning python point-cloud 3d-shape classification segmentation tensorflow research-code linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="charlesq34/pointnet2")