# PRBonn/lidar-bonnetal

Semantic and Instance Segmentation of LiDAR point clouds for autonomous driving

Repository: https://github.com/PRBonn/lidar-bonnetal
Canonical: https://ross.abutalabs.com/products/lidar-bonnetal
Homepage: http://semantic-kitti.org
Language: Python
License: MIT
License Family: permissive
Topics: lidar, deep-learning, ptcl, segmentation, dataset, semantic
Archived: true
Last push: 2024-08-05T16:44:00+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2597, "days_push": 758, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1037, forks 213 (observed 2026-08-28T04:03:19.514873+00:00)

## What it is
A deep learning framework for training and deploying semantic segmentation of LiDAR point clouds using range-image representations, developed by University of Bonn researchers. It includes pretrained models for the SemanticKITTI benchmark, but the repository has been archived and is no longer maintained.

## Use cases
- segment lidar point clouds for autonomous driving
- train a semantic segmentation model on SemanticKITTI
- run pretrained lidar segmentation models like SqueezeSeg or darknet
- label road scenes from automotive lidar scans
- benchmark point cloud segmentation with range images
- apply kNN post-processing to lidar segmentation predictions

## When to choose
- you need a proven baseline for SemanticKITTI-style range-image segmentation
- you want pretrained models for automotive lidar semantic segmentation
- you are doing research comparing lidar segmentation approaches

## When to avoid
- you need actively maintained code or support - the repo is archived
- you need instance or panoptic segmentation out of the box
- you work with point-cloud-native architectures rather than range images

## Facets
- artifact type: library
- maturity: abandoned
- function: deep-learning, computer-vision, image-processing, machine-learning
- domain: autonomous-vehicles, computer-vision, deep-learning, robotics
- platform: python
- tags: lidar, point-cloud, semantic-segmentation, range-images, semantickitti, autonomous-driving, pretrained-models, linux, gpu

## Member repositories
- PRBonn/lidar-bonnetal (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:19.514873+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 2026-08-30T07:04:20.942254+00:00, confidence not recorded.
  - readme: https://github.com/PRBonn/lidar-bonnetal (fetched 2026-08-28T04:03:19.514873+00:00, sha c1ac9ee8d4e8)
  - homepage: http://semantic-kitti.org (fetched 2026-08-29T13:05:22.724109+00:00, sha 3e025a6b5b00)
- Data as of 2026-08-30T08:39:29.467469+00:00.