# charlesq34/pointnet

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

Repository: https://github.com/charlesq34/pointnet
Canonical: https://ross.abutalabs.com/products/pointnet
Language: Python
License: NOASSERTION
License Family: other
Topics: point-cloud, classification, segmentation, neural-network, tensorflow, geometry-processing
Last push: 2023-11-30T03:26:15+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3501, "days_push": 1007, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5459, forks 1489 (observed 2026-08-28T04:09:19.441788+00:00)

## What it is
Reference implementation of PointNet, a neural network architecture that directly consumes unordered 3D point clouds for classification and part segmentation. Released with training code for ModelNet40 classification and ShapeNet Part segmentation.

## Use cases
- classify 3D shapes from point clouds
- segment parts of 3D objects
- run semantic parsing on point cloud scenes
- learn a deep learning model for point sets
- reproduce PointNet CVPR 2017 results

## When to choose
- you need the original PointNet implementation for research or benchmarking
- you work with raw point clouds in TensorFlow 1.x
- you want a baseline for point cloud classification or segmentation

## When to avoid
- you need a maintained framework on modern TensorFlow or PyTorch
- you want production-ready 3D deep learning tooling
- you need recent point cloud architectures like PointNet++ or transformers

## Facets
- artifact type: library
- maturity: maintenance
- function: deep-learning, machine-learning, image-processing
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: point-cloud, 3d-classification, part-segmentation, tensorflow, cvpr-2017, research-code, linux, gpu

## Member repositories
- charlesq34/pointnet (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:19.441788+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:56:47.230003+00:00, confidence not recorded.
  - readme: https://github.com/charlesq34/pointnet (fetched 2026-08-28T04:09:19.441788+00:00, sha f0d2c6ac3916)
- Data as of 2026-08-30T08:39:29.467469+00:00.