reading-sensor-pointclouds

Official

Read and map sensor PointCloud data.

AuthorNVIDIA-Omniverse
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Access and read PointCloud outputs from lidar or radar sensors, mapping composite render-var tensors such as Coordinates, Counts, Intensity, RCS, RadialVelocityMs, and TimeOffsetNs to usable memory spaces, and handling per-point validity and memory lifetime. For channel meanings and units, see the related interpreting-lidar-pointclouds and interpreting-radar-pointclouds skills.

Core Features & Use Cases

  • Read PointCloud channels (Coordinates, Counts, Intensity, TimeOffsetNs) and map them to CPU or CUDA memory.
  • Slice valid entries using Counts and Flags and handle per-point validity for downstream processing or visualization.
  • Use with Python or C/C++ examples to access and interpret PointCloud data in sensor pipelines.

Quick Start

Load a lidar PointCloud, map it to CPU memory, and print coordinates and counts.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: reading-sensor-pointclouds
Download link: https://github.com/NVIDIA-Omniverse/ovrtx/archive/main.zip#reading-sensor-pointclouds

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.