NVlabs/FB-BEV

Official PyTorch implementation of FB-BEV & FB-OCC - Forward-backward view transformation for vision-centric autonomous driving perception

43
/ 100
Emerging

This helps autonomous driving engineers precisely understand the environment around a self-driving vehicle using only camera footage. It takes in raw camera video streams from the vehicle and outputs a detailed 3D map of objects and occupied spaces in the vehicle's surroundings. It's for engineers developing and testing autonomous driving systems.

783 stars. No commits in the last 6 months.

Use this if you need to enhance your autonomous driving system's ability to detect objects and predict occupied spaces from vision data alone, especially for robust real-world performance.

Not ideal if your autonomous driving system relies primarily on LiDAR or radar for environmental perception and you are not integrating camera-based 3D scene understanding.

autonomous-driving vehicle-perception 3d-object-detection occupancy-prediction computer-vision-for-AV
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

783

Forks

69

Language

Python

License

Last pushed

Mar 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/NVlabs/FB-BEV"

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