semantic-labels

Assign semantic class and label metadata to USD prims via SemanticsAPI.

201|25|Updated Dec 18, 2025
One-click install
npx skills add https://github.com/NVIDIA-Omniverse/ovrtx --skill semantic-labels
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: semantic-labels
Source: https://github.com/NVIDIA-Omniverse/ovrtx/tree/main/.agents/skills/semantic-labels
Command: npx skills add https://github.com/NVIDIA-Omniverse/ovrtx --skill semantic-labels

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Assigning consistent semantic class and label metadata to USD prims is essential for reliable semantic segmentation and ground-truth generation. This Skill provides a repeatable workflow to author SemanticsAPI data and produce labeled outputs for rendering.

Core Features & Use Cases

  • Apply SemanticsAPI class and label instances to prims to drive semantic segmentation.
  • Preserve source assets by using inline root layers and over prims in a composed scene.
  • Generate SemanticSegmentation and SemanticIdMap outputs on a RenderProduct for training or evaluation.

Quick Start

Build an inline USD scene, apply SemanticsAPI labels to the target prims, and render to produce SemanticSegmentation and SemanticIdMap outputs.

Frequently Asked Questions about semantic-labels

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I assign semantic labels to USD prims for segmentation?

Assign semantic class and label metadata to USD prims using SemanticsAPI to drive semantic segmentation outputs. You apply SemanticsAPI instances to target prims in your composed scene to generate ground-truth annotations.

How do I preserve source USD assets when applying semantic annotations?

Preserve source USD assets by using inline root layers and over prims for overrides in a composed scene. This workflow ensures your original files remain untouched while authoring SemanticsAPI data.

What render outputs do I need to generate semantic segmentation data?

Configure RenderProduct outputs specifically for SemanticSegmentation and SemanticIdMap to generate semantic segmentation data. These render products capture the labeled ground-truth data required for training or evaluation.

Can I use Python workflows to apply SemanticsAPI to runtime-composed USD scenes?

You can use Python workflows to apply SemanticsAPI labels to runtime-composed USD scenes and inline sublayers. The workflow supports mixed Python and USD environments for labeling objects and generating annotations.

Does semantic label inheritance affect USD segmentation outputs?

Semantics inheritance affects USD segmentation outputs when applying SemanticsAPI class and label instances to prims. Attention to semantics inheritance is required to ensure consistent semantic segmentation and ground-truth generation across the scene hierarchy.