@@ -19,11 +19,11 @@ For business inquiries, please visit our website and submit the form: [NVIDIA Re
...
@@ -19,11 +19,11 @@ For business inquiries, please visit our website and submit the form: [NVIDIA Re
## Requirements
## Requirements
- Both Windows and Linux are supported.
- Both Windows and Linux are supported.
-[CUDA](https://developer.nvidia.com/cuda-toolkit)__v10.2 or higher__, a __C++14__ capable compiler, and [CMake](https://cmake.org/)__v3.19 or higher__.
-__NVIDIA GPU__ with __compute capability 75 or higher (RTX 20XX or newer)__. All shown results come from an RTX 3090.
-A high-end NVIDIA GPU that supports TensorCores and has a large amount of memory. The framework was tested primarily with an RTX 3090.
-__[CUDA](https://developer.nvidia.com/cuda-toolkit) v10.2 or higher__, a __C++14__ capable compiler, and __[CMake](https://cmake.org/) v3.19 or higher__.
- __(optional)__[Python](https://www.python.org/)__3.7 or higher__ for interactive bindings. Also, run `pip install -r requirements.txt`.
- __(optional) [Python](https://www.python.org/) 3.7 or higher__ for interactive bindings. Also, run `pip install -r requirements.txt`.
- On some machines, `pyexr` refuses to install via `pip`. This can be resolved by installing OpenEXR from [here](https://www.lfd.uci.edu/~gohlke/pythonlibs/#openexr).
- On some machines, `pyexr` refuses to install via `pip`. This can be resolved by installing OpenEXR from [here](https://www.lfd.uci.edu/~gohlke/pythonlibs/#openexr).
- __(optional)__[OptiX](https://developer.nvidia.com/optix)__7.3 or higher__ for faster mesh SDF training. Set the environment variable `OptiX_INSTALL_DIR` to the installation directory if it is not discovered automatically.
- __(optional) [OptiX](https://developer.nvidia.com/optix) 7.3 or higher__ for faster mesh SDF training. Set the environment variable `OptiX_INSTALL_DIR` to the installation directory if it is not discovered automatically.
If you are using Linux, install the following packages
If you are using Linux, install the following packages