Python: SPG Grayscale#

The “hello world” of Sensor Processing Graphs. A custom CUDA kernel converts the renderer’s LdrColor AOV to grayscale entirely on the GPU and publishes the result as a new LdrGrayscale AOV. This is the minimal three-file SPG shader (.cu kernel, .cu.lua launch script, .usda shader definition) wired into a RenderProduct.

This example uses the deprecated renderer scene-loading API so it can remain focused on SPG authoring. Use the 0.3-to-0.4 migration skill when moving scene management to ovstage.

“Create the smallest useful SPG example: a CUDA kernel that converts the LdrColor render output to grayscale, wired into a RenderProduct and read back from Python as a new AOV.”

SPG grayscale example output

Prerequisites#

  • Python 3.10-3.13

  • uv

  • An NVIDIA RTX-capable GPU and a supported driver

Running#

uv run main.py

The first step compiles the CUDA kernel with NVRTC and can block for up to a minute on a fresh shader cache. A successful run writes _output/input.png and _output/grayscale.png.

See the Overview documentation for the full authoring reference.

On this page