oooolga/Ctrl-V

👆Pytorch implementation of "Ctrl-V: Higher Fidelity Video Generation with Bounding-Box Controlled Object Motion"

31
/ 100
Emerging

This project helps researchers and developers in autonomous driving simulate realistic video footage of vehicles and pedestrians. You input existing video datasets, and it outputs new videos where object movements, like cars changing lanes or pedestrians crossing, are precisely controlled by bounding boxes. This is ideal for those working on training and testing self-driving car algorithms.

No commits in the last 6 months.

Use this if you need to generate high-fidelity video scenarios with specific, controlled object motion for autonomous vehicle research and development.

Not ideal if you are looking for a general-purpose video generation tool not focused on autonomous driving datasets or fine-grained object control.

autonomous-vehicles video-simulation motion-control dataset-generation computer-vision-research
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

33

Forks

2

Language

Python

License

Apache-2.0

Last pushed

Jul 28, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/oooolga/Ctrl-V"

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