AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Engineering › torch-points3d
✦ Free & open sourceEngineering

torch-points3d

A PyTorch framework for deep learning tasks on 3D point clouds like segmentation, classification, and registration.

Deep learning modular framework for 3D point cloud analysis

Build, train, and benchmark point cloud neural networks using PyTorch Geometric and Facebook Hydra.

Free forever · source-available · Licence not stated in the repository
✓ Needs IT✓ Browser-based✓ Real-time collaboration
7.3
ZEKAI
Essential for 3D AI engineers
Free & open source · Engineering
Ease of setup4
Usefulness8
Maintenance9.5
Community7.5
★ 2,712
GITHUB
Oct 2026
UPDATED
Licence not stated in the repository
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

torch-points3d is an open-source Python framework designed for running advanced neural network architectures on 3D point cloud datasets. It combines PyTorch Geometric and Facebook Hydra to help technical teams train models for 3D object detection, segmentation, and registration. You should use it if you need a modular code structure for 3D spatial analysis.

Runs on
Cross-platform
Hosting
Self-host
Languages
Python
License
Licence not stated in the repository

What it is

The framework unifies popular 3D deep learning models—including PointNet++, KPConv, RandLA-Net, and MinkowskiEngine—into a single modular codebase. It organizes datasets and architectures by specific 3D tasks such as panoptic segmentation, classification, object detection, and registration. You can run training or evaluation pipelines using integrated support for benchmark datasets like ScanNet, S3DIS, and ShapeNet.

Who it's for

This tool suits machine learning engineers and 3D vision researchers analyzing LiDAR or photogrammetry scan data for engineering and architectural contexts. It is not designed for non-technical users or those looking for a graphical 3D modeling application. Teams without dedicated GPU hardware and Python development experience will find the setup challenging.

Key features

Task-based code architecture

Organizes models and dataset loaders into clean subfolders for segmentation, classification, registration, object detection, and panoptic tasks.

Multi-model architecture support

Implements established 3D architectures including PointNet, PointNet++, KPConv, RandLA-Net, RSConv, and MinkowskiEngine.

Hydra configuration integration

Uses Facebook Hydra to manage experiment configurations, dataset parameters, and model hyperparameters reproducibly.

Benchmark dataset integration

Includes built-in dataset handling for standard 3D benchmarks such as ScanNet, S3DIS, and ShapeNet.

How to start

Up and running in 3 steps

1
Set up a CUDA-enabled GPU environment natively or pull the recommended PyTorch Docker image.
2
Install the core package using pip install torch-points3d alongside PyTorch and PyTorch Geometric.
3
Configure your model and dataset parameters inside the conf directory and launch training with train.py.
Real talk

Our honest verdict

What's great

  • Implements a wide range of state-of-the-art 3D point cloud models in a unified API
  • Configured with Facebook Hydra for modular experiment management and reproducibility
  • Supports key 3D tasks including semantic segmentation, panoptic segmentation, and 3D object detection
  • Provides pre-built Docker setup instructions to handle complex PyTorch and CUDA dependencies

Where it falls short

  • Requires dedicated GPU hardware with CUDA 10+ and specialized sparse convolution backends
  • Complex dependency stack involving PyTorch Geometric and C++ compilation steps can complicate setup
  • Lacks a graphical user interface, requiring pure Python and CLI configuration
  • Repository metadata does not state an explicit open-source license
Cost

Pricing & license

torch-points3d is free to download and use directly from GitHub. There are no commercial hosted tiers provided by the maintainers, so your main cost will be the GPU compute infrastructure required for training.

Paid work

Open remote AI-training roles

877 open remote AI-training roles, updated November 16, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives

These reviewed AI tools do the same job instantly — from our scored directory.

Get more

Use it, or have us set it up

📄 Free PDF: torch-points3d for Engineering
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure torch-points3d for you — and train your team.
Get it done for you ↗
Questions

FAQ

What point cloud tasks does torch-points3d support?

It supports 3D semantic segmentation, classification, part segmentation, 3D object detection, panoptic segmentation, and point cloud registration.

Which benchmark datasets are supported out of the box?

The framework includes dataset modules for ScanNet, S3DIS (in multiple sub-formats), and ShapeNet.

Do I need a GPU to run torch-points3d?

Yes, GPU hardware with CUDA 10 or higher is required for effective model training and sparse convolution operations.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Engineering — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google