# yangyanli/PointCNN

PointCNN: Convolution On X-Transformed Points (NeurIPS 2018)

Repository: https://github.com/yangyanli/PointCNN
Canonical: https://ross.abutalabs.com/products/pointcnn
Homepage: https://arxiv.org/abs/1801.07791
Language: Python
License: NOASSERTION
License Family: other
Topics: pointcloud, convolutional-neural-networks, deep-neural-networks, machine-learning, autonomous-driving, segmentation, point-cloud, scannet, shapenet, classification, robotics
Last push: 2026-03-12T12:31:09+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 71, release rhythm 8, longevity 100
- inputs: {"age_days": 3298, "days_push": 174, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1434, forks 358 (observed 2026-08-28T04:04:43.362732+00:00)

## What it is
PointCNN is a deep learning framework for feature learning from 3D point clouds, applying convolution on X-transformed points to handle their irregular, unordered structure. It achieved state-of-the-art results on benchmarks like ModelNet40, ScanNet, and ShapeNet Parts for classification and segmentation tasks.

## Use cases
- classify 3D point clouds on ModelNet40
- segment parts of 3D shapes from ShapeNet
- semantic segmentation of indoor scenes from point clouds
- label voxels in ScanNet scans
- process LiDAR point clouds for autonomous driving
- segment aerial point clouds for 3D city mapping
- learn features from unordered 3D point sets

## When to choose
- you need a proven point cloud CNN for classification or segmentation benchmarks
- you want pretrained models for point cloud tasks
- you're doing research on 3D feature learning from unordered point sets
- you need point cloud segmentation integrated into GIS workflows like ArcGIS

## When to avoid
- you want the latest architecture - the authors recommend PointCNN++ instead
- you need a permissively licensed library - the license is non-standard
- you need active development or modern framework support
- you want a PyTorch-native implementation - use the PyTorch Geometric port instead

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, computer-vision, image-processing
- domain: computer-vision, machine-learning, deep-learning, autonomous-vehicles, robotics
- platform: python
- tags: point-cloud, 3d-deep-learning, pointcloud-segmentation, pointcloud-classification, neurips-2018, x-transformation, tensorflow, linux, gpu

## Member repositories
- yangyanli/PointCNN (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:43.362732+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 2026-08-30T04:36:56.136200+00:00, confidence not recorded.
  - readme: https://github.com/yangyanli/PointCNN (fetched 2026-08-28T04:04:43.362732+00:00, sha 54378e8f2463)
  - homepage: https://arxiv.org/abs/1801.07791 (fetched 2026-08-29T11:48:00.452970+00:00, sha 92b258e2e0db)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T11:48:00.455856+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T11:48:00.459194+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T11:48:00.460946+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T11:48:00.457648+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.