MasterHow/OccFiner

Offboard Occupancy Refinement with Hybrid Propagation for Autonomous Driving

27
/ 100
Experimental

This helps autonomous vehicle engineers and researchers create extremely accurate 3D maps of a car's surroundings. It takes raw camera footage and initial 3D predictions, then refines them into a much more precise and complete occupancy map, which details every object and its semantic class in the scene. This is used by professionals working on self-driving car perception and mapping.

No commits in the last 6 months.

Use this if you need to significantly improve the accuracy and completeness of 3D semantic scene completion maps generated from camera data for autonomous driving applications.

Not ideal if you are looking for an onboard, real-time solution for occupancy prediction, as this tool is designed for offboard, post-processing refinement.

autonomous-driving 3d-mapping scene-understanding robotics-perception computer-vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

16

Forks

1

Language

License

MIT

Last pushed

Feb 10, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MasterHow/OccFiner"

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