PRBonn/lidar-bonnetal

Health v2 · maintenance only

Flags: no_releases archived

Adoption not part of the score

1037 stars · 213 forks observed · 2026-08-28

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

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 It includes pretrained models for the SemanticKITTI benchmark, but the repository has been archived and is no longer maintained.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

library · maturity abandoned

deep-learning computer-vision image-processing machine-learning autonomous-vehicles computer-vision deep-learning robotics python lidar point-cloud semantic-segmentation range-images semantickitti autonomous-driving pretrained-models linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="PRBonn/lidar-bonnetal")