# yanx27/Pointnet_Pointnet2_pytorch

PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.

Repository: https://github.com/yanx27/Pointnet_Pointnet2_pytorch
Canonical: https://ross.abutalabs.com/products/pointnet_pointnet2_pytorch
Language: Python
License: MIT
License Family: permissive
Topics: pointnet, pointnet2, pointcloud, segmentation, s3dis, modelnet, shapenet, pytorch, classification, visualization, point-cloud
Last push: 2024-04-24T17:21:53+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": 2739, "days_push": 861, "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 4936, forks 1020 (observed 2026-08-28T04:09:02.696199+00:00)

## What it is
A pure PyTorch implementation of the PointNet and PointNet++ deep learning architectures for point cloud processing. It includes training and testing code for classification (ModelNet10/40), part segmentation (ShapeNet), and semantic segmentation (S3DIS) with pre-trained models.

## Use cases
- classify 3D point clouds with PointNet
- train PointNet++ on ModelNet40
- semantic segmentation of indoor scenes with S3DIS
- part segmentation on ShapeNet
- reproduce PointNet paper results in PyTorch
- learn point cloud deep learning
- visualize point cloud segmentation results

## When to choose
- you need a faithful, well-starred PyTorch reimplementation of PointNet/PointNet++
- you want pre-trained models for point cloud classification or segmentation benchmarks
- you are learning or teaching 3D deep learning on point sets

## When to avoid
- you need state-of-the-art point cloud models beyond PointNet++
- you want a maintained library with recent updates and broad API support
- you need production-ready 3D perception pipelines rather than research code

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing, data-visualization
- domain: deep-learning, computer-vision, machine-learning, artificial-intelligence
- platform: python
- tags: pointnet, pointnet2, point-cloud, pytorch, semantic-segmentation, classification, modelnet, shapenet, s3dis, 3d-deep-learning, linux, gpu

## Member repositories
- yanx27/Pointnet_Pointnet2_pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:02.696199+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 2026-08-29T18:17:57.369615+00:00, confidence not recorded.
  - readme: https://github.com/yanx27/Pointnet_Pointnet2_pytorch (fetched 2026-08-28T04:09:02.696199+00:00, sha a885a0087ecf)
- Data as of 2026-08-30T08:39:29.467469+00:00.