# url-kaist/patchwork-plusplus

Patchwork++: Fast and robust ground segmentation method for 3D LiDAR scans. @ IROS'22

Repository: https://github.com/url-kaist/patchwork-plusplus
Canonical: https://ross.abutalabs.com/products/patchwork-plusplus
Language: C++
License: BSD-2-Clause
License Family: permissive
Topics: 3d-lidar, ground-segmentation, point-cloud, lidar, segmentation, ground, ground-removal, detection, ground-detection
Last push: 2026-05-23T06:46:01+00:00

## Health v2 (maintenance only)
Score: 87/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 83, release rhythm 85, longevity 100
- inputs: {"age_days": 1650, "days_push": 102, "days_rel": 102, "gap_med": 1, "n_releases_24m": 8}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1051, forks 161 (observed 2026-08-28T04:03:23.096045+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: computer-vision, image-processing, sdk
- domain: robotics, autonomous-vehicles, computer-vision
- platform: cpp, python, windows
- tags: lidar, point-cloud, ground-segmentation, ros2, 3d-perception, iros-2022, algorithms, linux, macos, ros

## Member repositories
- url-kaist/patchwork-plusplus (main) score 87

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:23.096045+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:00:14.341271+00:00, confidence not recorded.
  - readme: https://github.com/url-kaist/patchwork-plusplus (fetched 2026-08-28T04:03:23.096045+00:00, sha 003f96f6645e)
- Data as of 2026-08-30T08:39:29.467469+00:00.