ovrtx is a lightweight C and Python SDK for Omniverse RTX, allowing developers to integrate RTX sensor simulation and visualization easily into their applications.
Omniverse RTX provides real-time, physically accurate sensor simulation and rendering for Physical AI, targeting robotics learning, synthetic data generation, and industrial and design workflows.
Note
ovrtx is currently pre-release software.
- Physically accurate simulation of cameras, lidar, radar, ultrasonic and more sensors.
- Scalable simulation performance from reinforcement learning in-the-loop with tens of thousands of frames per second, through real-time, photorealistic, interactive viewport and navigation, to offline predictive rendering.
- OpenUSD scene description allowing interchange with a vast ecosystem of content creation, CAD and simulation tools.
- Easy integration with Python simulation and learning ecosystem.
During Early Access, we recommend using the uv Python package and project manager. All the examples in this repository contain pyproject.toml files that are tested with uv.
Python 3.10–3.13 is required.
To get started, first clone this repository and run the first example with uv:
git clone https://github.com/NVIDIA-Omniverse/ovrtx.git
cd ovrtx/examples/python/minimal
uv run main.pyThe minimal example shows how to create the renderer, load an OpenUSD scene and render a single image, copying the results back to the CPU for display.
Note that the first time a program built against ovrtx is run, it will compile and cache necessary shaders, which may take some time depending on your system. Subsequent runs will use the cached shaders and will be fast.
The C/C++ examples require CMake and a development environment. On Windows this is provided by Visual Studio 2017 or newer. On Linux (Ubuntu):
sudo apt-get build-essential cmakeTo get started, first clone this repository and build and run the first example using CMake:
git clone https://github.com/NVIDIA-Omniverse/ovrtx.git
cd ovrtx/examples/c/minimal
cmake -B build Then, on Windows:
cmake --build build --config Release
.\build\Release\minimal.exe
On Linux:
cmake --build build --config Release
./build/minimal
The minimal example shows how to create the renderer, load an OpenUSD scene and render a single image, copying the results back to the CPU for writing out as a PNG.
The resulting image will be written to ./out.png and can be inspected with any image viewer.
Note that the first time a program built against ovrtx is run, it will compile and cache necessary shaders, which may take some time depending on your system. Subsequent runs will use the cached shaders and will be fast.
Further examples using both the C and Python APIs are available in the examples directory. See the individual examples for building and usage instructions.
The Releases page of this repository contains binary builds for the official releases of the ovrtx C library and the corresponding Python wheels. These binaries are provided for the supported platforms:
- Windows x86_64
- Linux x86_64
- Linux aarch64
The libraries require a compatible NVIDIA RTX-capable GPU with a compatible NVIDIA driver on the system to be able to initialize correctly. More detailed system requirements can be found at https://docs.omniverse.nvidia.com/dev-guide/latest/common/technical-requirements.html
The skills directory contains a series of Skills to help AI coding agents to understand how to use the API (and they're useful for humans too). Copy this directory to your project and point your agent at it.
Documentation is published at https://nvidia-omniverse.github.io/ovrtx
cd docs
make htmlThen, to view the built docs:
uv run python -m http.server 8000 -d _build/htmlThen open http://localhost:8000/ in a browser.
https://forums.developer.nvidia.com/c/omniverse/300
To be announced
At this time this project is not open to external contributions.
NVIDIA Corporation
The software and materials are governed by the NVIDIA Software License Agreement and the Product-Specific Terms for NVIDIA Omniverse.
This project will download and install additional third-party open source software projects. Review the license terms of these open source projects before use.