Kaolin

Visit Tool

Kaolin is a PyTorch library for accelerating 3D deep learning research. It provides a PyTorch API for working with various 3D representations and includes GPU-optimized operations like differentiable rendering and fast conversions.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Yes

Skill level

Technical

About

What is kaolin?

Kaolin is a PyTorch library developed by NVIDIA GameWorks, designed to accelerate 3D deep learning research. It offers a comprehensive PyTorch API for handling diverse 3D representations, including meshes, point clouds, and voxel grids. The library features a growing collection of GPU-optimized operations such as modular differentiable rendering, efficient conversions between 3D formats, and advanced data loading capabilities. Key functionalities also include a differentiable camera API, lighting with spherical harmonics and Gaussians, and a powerful quadtree acceleration structure called Structured Point Clouds. Kaolin provides an interactive 3D visualizer for Jupyter notebooks and a convenient batched mesh container, making it a versatile tool for researchers and developers in 3D AI.

Best used for

Ideal for developers who need to accelerate 3D deep learning research, implement differentiable rendering, and perform fast conversions between 3D representations. Especially valuable for those working with PyTorch and requiring GPU-optimized operations for complex 3D tasks like physics simulation and interactive visualization.

Common actions

accelerate 3D deep learning

perform differentiable rendering

convert 3D representations

simulate 3D physics

visualize 3D data

github copilot"AI Agents"face swappingcollaborationautomated workflowdeepfakeworkflowslow-code/no-codeopen-source

Capabilities

Key features

PyTorch API for 3D
GPU-optimized operations
Differentiable rendering
Fast 3D conversions
Differentiable camera API
Interactive 3D visualizer
Physics simulation

Target Audience

developer

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What are the licensing terms for Kaolin?

Most of Kaolin's repository is under the Apache v2.0 license, allowing for commercial use. However, components within `kaolin/non_commercial` are restricted to non-commercial usage for research and evaluation purposes under the NSCL license. FlexiCubes, previously restricted, is now also under Apache v2.0.

How do I install Kaolin?

Kaolin supports installation with wheels. You can install it using pip by specifying the Kaolin version and replacing `TORCH_VERSION` and `CUDA_VERSION` with your specific PyTorch and CUDA versions. For example, `pip install kaolin==0.18.0 -f https://nvidia-kaolin.s3.us-east-2.amazonaws.com/torch-2.8.0_cu128.html`.

What are some of the new features in Kaolin v0.18.0?

Version 0.18.0 introduces collisions to the physics module and a new conversion from 3D gaussians to voxelgrids, enhancing accuracy in densifying functions. It also includes updated tutorials for physics simulation and Flexicubes license changes, making it usable for commercial purposes.

Trending

Subcategories trending in Coding & Development

Open Source & Models DevOps & Infrastructure No-Code / Low-Code Testing & QA Backend & APIs Prompt Engineering

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce