NVIDIAGameWorks/kaolin
A PyTorch Library for Accelerating 3D Deep Learning Research
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.
Stars
5,056
Forks
618
Language
Python
License
Apache-2.0
Category
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.
Recent Releases
Related frameworks
Jim137/qkan
PyTorch implementation of QKAN "Quantum-inspired Kolmogorov-Arnold Network"...
AntonioTepsich/Convolutional-KANs
This project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN)...
lgy112112/ikan
ikan: many kan variants for every body
Indoxer/LKAN
Variations of Kolmogorov-Arnold Networks
RomanBresson/KAGNN
This is the official repository for our paper KAGNNs: Kolmogorov-Arnold Networks meet Graph Learning.