# fxia22/pointnet.pytorch

pytorch implementation for "PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation"  https://arxiv.org/abs/1612.00593

Repository: https://github.com/fxia22/pointnet.pytorch
Canonical: https://ross.abutalabs.com/products/pointnetpytorch
Language: Python
License: MIT
License Family: permissive
Last push: 2023-03-23T19:29:57+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3428, "days_push": 1259, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2354, forks 632 (observed 2026-08-28T04:06:40.521640+00:00)

## What it is
A PyTorch implementation of PointNet, the deep learning model for classification and segmentation of 3D point sets. It includes training scripts for ModelNet40 classification and ShapeNet part segmentation, plus a C++ visualization tool.

## Use cases
- classify 3d point clouds with pointnet in pytorch
- train pointnet on modelnet40
- run part segmentation on shapenet point clouds
- reproduce pointnet paper results
- learn how pointnet works from code
- segment parts of 3d objects from point sets

## When to choose
- you want a simple, readable PyTorch port of the original PointNet
- you need to train or evaluate point cloud classification or segmentation on ModelNet40 or ShapeNet
- you are studying or teaching point cloud deep learning

## When to avoid
- you need state-of-the-art point cloud models like PointNet++ or transformers
- you need production-grade training pipelines with modern PyTorch features
- you need active development or frequent updates

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, computer-vision
- platform: python
- tags: pointnet, point-cloud, pytorch, 3d-classification, 3d-segmentation, modelnet40, shapenet

## Member repositories
- fxia22/pointnet.pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:40.521640+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 2026-08-30T02:36:27.876855+00:00, confidence not recorded.
  - readme: https://github.com/fxia22/pointnet.pytorch (fetched 2026-08-28T04:06:40.521640+00:00, sha bdb859224aaf)
- Data as of 2026-08-30T08:39:29.467469+00:00.