nv-tlabs/SCube

[NeurIPS 2024] SCube: Instant Large-Scale Scene Reconstruction using VoxSplats

40
/ 100
Emerging

This project helps quickly create detailed 3D models of large outdoor environments using existing image and LiDAR data from autonomous driving systems. You input a sequence of camera images and LiDAR scans, and it outputs a complete 3D scene reconstruction ready for visualization or further analysis. It's designed for researchers and engineers working on autonomous vehicles, robotics, or large-scale virtual environment generation.

521 stars. No commits in the last 6 months.

Use this if you need to generate high-fidelity, instant 3D reconstructions of complex outdoor scenes from sensor data, particularly for autonomous vehicle development or simulation.

Not ideal if you're looking to reconstruct small, indoor environments or if you don't have access to extensive image and LiDAR datasets from moving platforms.

autonomous-driving 3d-reconstruction robotics environmental-mapping sensor-fusion
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

521

Forks

25

Language

Python

License

Last pushed

Oct 14, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/nv-tlabs/SCube"

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