Reconstruct segmented 3D scenes from RGB images.
What it does
Produces trained models and 3D scene segmentations from posed RGB images using NVPanoptix3D.
When to use it
Use for training, evaluation, export, or inference with a TAO NVPanoptix3D model.
How to use it
Give it the action's dataset, specification, and model files as applicable; it runs training, evaluation, inference, or export into configured output paths.
What you provide
- Your files
What you need · 6
Requires Docker for the container-native launch; no host Python or TAO SDK is required.
Requires nvidia-container-toolkit for GPU container execution.
The hardware guidance specifies at least two GPUs with 40GB+ VRAM per GPU; four GPUs and A100 hardware are recommended.
Must run first for a standalone installation when the session was not initialized by the TAO skill bank plugin.
Access · 0
No additional actions listed.