# charlesq34/pointnet2

PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

Repository: https://github.com/charlesq34/pointnet2
Canonical: https://ross.abutalabs.com/products/pointnet2
Language: Python
License: NOASSERTION
License Family: other
Topics: point-cloud, deep-learning, classification, segmentation, 3d-shape
Last push: 2022-08-26T00:39:24+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": 3289, "days_push": 1469, "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 3700, forks 931 (observed 2026-08-28T04:08:14.922949+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: deep-learning, machine-learning, computer-vision
- domain: computer-vision, deep-learning, machine-learning
- platform: python
- tags: point-cloud, 3d-shape, classification, segmentation, tensorflow, research-code, linux, gpu

## Member repositories
- charlesq34/pointnet2 (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:14.922949+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 2026-08-29T18:31:02.620714+00:00, confidence not recorded.
  - readme: https://github.com/charlesq34/pointnet2 (fetched 2026-08-28T04:08:14.922949+00:00, sha d6568d2d4397)
- Data as of 2026-08-30T08:39:29.467469+00:00.