OpenDriveLab/PersFormer_3DLane

[ECCV 2022 Oral] Perspective Transformer on 3D Lane Detection

50
/ 100
Established

This helps autonomous vehicle developers accurately detect 3D lane lines from a single camera feed. It takes raw camera images as input and outputs precise 3D coordinates of lane markings, helping self-driving systems understand road structure. It's designed for engineers building robust perception systems for autonomous driving.

495 stars. No commits in the last 6 months.

Use this if you need to detect 3D lane lines from monocular camera data with high accuracy for autonomous driving applications.

Not ideal if you are looking for a system that uses multiple sensors (like LiDAR or radar) for lane detection or if your application isn't in autonomous driving.

autonomous-driving lane-detection vehicle-perception robotics computer-vision
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

495

Forks

85

Language

Python

License

Apache-2.0

Last pushed

Jul 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/OpenDriveLab/PersFormer_3DLane"

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