csiro-robotics/WildScenes

[IJRR2024] The official repository for the WildScenes: A Benchmark for 2D and 3D Semantic Segmentation in Natural Environments

37
/ 100
Emerging

This project offers a comprehensive dataset and benchmarks for researchers and engineers developing robotic perception systems for natural, unstructured environments. It provides richly annotated 2D images and 3D LiDAR point clouds of outdoor scenes, along with tools to visualize this data. The primary users are robotics researchers or engineers working on autonomous systems that operate in wildland, agricultural, or disaster relief settings.

No commits in the last 6 months.

Use this if you are developing or evaluating deep learning models for semantic segmentation on real-world natural environment data, particularly for applications like robotic navigation or environmental monitoring.

Not ideal if you are looking for a pre-built, ready-to-deploy solution for a specific application, as this is a research benchmark dataset and framework.

robotics environmental-monitoring agricultural-automation search-and-rescue autonomous-navigation
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

83

Forks

7

Language

Python

License

Last pushed

Jun 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/csiro-robotics/WildScenes"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.