url-kaist/patchwork-plusplus

Health v2 · maintenance only

Adoption not part of the score

1051 stars · 161 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Patchwork++ is a fast, robust, and self-adaptive ground segmentation algorithm for 3D LiDAR point clouds, published at IROS 2022. It provides C++ and Python APIs plus a ROS2 wrapper for removing or detecting ground in point cloud data.

Use cases

• segment ground from 3d lidar point clouds
• remove ground points before object detection
• estimate ground plane in autonomous driving lidar data
• preprocess point clouds for obstacle detection
• run ground segmentation in ros2
• use lidar ground segmentation from python

When to choose

• you need fast, real-time ground segmentation for LiDAR scans
• you want a self-adaptive algorithm robust to uneven terrain
• you work in ROS2 or need C++/Python bindings

When to avoid

• you need semantic segmentation of all point cloud classes, not just ground
• your input is camera imagery rather than 3D point clouds
• you need a GPU-accelerated deep-learning-based segmentation model

Facets

library · maturity active

computer-vision image-processing sdk robotics autonomous-vehicles computer-vision cpp python windows lidar point-cloud ground-segmentation ros2 3d-perception iros-2022 algorithms linux macos ros

Member repositories

For agents

markdown · JSON · MCP: product_card(name="url-kaist/patchwork-plusplus")