NVIDIAGameWorks/kaolin

A PyTorch Library for Accelerating 3D Deep Learning Research

64
/ 100
Established

This is a specialized tool for researchers and developers working on advanced 3D deep learning projects. It provides a suite of GPU-optimized operations for working with various 3D representations, such as meshes and point clouds. Researchers can input 3D data, apply differentiable rendering, physics simulations, and conversions between formats to accelerate their model development and experimentation.

5,056 stars. Actively maintained with 12 commits in the last 30 days.

Use this if you are developing or researching new 3D deep learning models and need a high-performance framework to handle 3D data representations, rendering, and physics simulations.

Not ideal if you are looking for a pre-built 3D application or a simple visualization tool without a deep learning development component.

3D computer vision deep learning research computer graphics robotics simulation virtual reality development
No Package No Dependents
Maintenance 17 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

5,056

Forks

618

Language

Python

License

Apache-2.0

Last pushed

Mar 13, 2026

Commits (30d)

12

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/NVIDIAGameWorks/kaolin"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.