nv-tlabs/InfiniCube

[ICCV 2025] InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models

39
/ 100
Emerging

This tool helps create realistic, dynamic 3D driving scenes from map data or existing driving trajectories. It takes map information or a camera path as input and generates a vivid 3D scene with dynamic elements like cars and pedestrians, outputting a playable 3D environment or video. This is ideal for researchers and engineers working on autonomous driving simulations or synthetic data generation.

119 stars.

Use this if you need to generate diverse, controllable, and large-scale synthetic 3D driving scenarios for testing autonomous vehicle systems or training AI models.

Not ideal if you are looking for a simple drag-and-drop tool for quick video editing or general 3D scene design unrelated to driving simulations.

autonomous-driving 3D-simulation synthetic-data-generation urban-planning-visualization robotics-testing
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 4 / 25

How are scores calculated?

Stars

119

Forks

2

Language

Python

License

Last pushed

Jan 23, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/nv-tlabs/InfiniCube"

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