cure-lab/MagicDrive

[ICLR24] Official implementation of the paper “MagicDrive: Street View Generation with Diverse 3D Geometry Control”

42
/ 100
Emerging

This tool helps researchers and engineers in autonomous driving generate realistic street-view images and videos. You provide details like camera angles, road layouts, and 3D object positions, along with text descriptions, and it creates consistent, high-fidelity driving scene visuals. It's ideal for those developing and testing 3D perception systems for self-driving cars.

1,166 stars. No commits in the last 6 months.

Use this if you need to create synthetic street-view data with precise control over 3D geometry and multi-camera consistency for tasks like training 3D object detection or BEV segmentation models.

Not ideal if you are looking for general-purpose image or video generation outside of the specific domain of autonomous driving street scenes and their associated 3D controls.

autonomous-driving synthetic-data-generation 3D-perception computer-vision robotics
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

1,166

Forks

51

Language

Python

License

Apache-2.0

Last pushed

Apr 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/cure-lab/MagicDrive"

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