Content Workflow Mesh Segmentation

Segment one fused triangular USD mesh into logical mesh prims by identifying visible parts, freezing deterministic geometry fragments, choosing per part between a registered image-mask seed produced through the image-generation skill and direct agentic signed fragment selection, and falsifying each provisional result with signed confuser evidence and held-out multi-view review before locking it. Use for fused-mesh semantic or material segmentation when Codex must control fallible image-generated masks and refine whole-fragment labels.

NVIDIA-Omniverse Updated 245 repo stars
USD Content Agents workflow overview from geometry through validation

File contents

nvidia-omniverse/usd-content-agents commit 1129644ac2

Frequently asked questions

npx get-skill add nvidia-omniverse/content-workflow-mesh-segmentation