kavisha725/MBNSF

[3DV 2024] Repository for "Multi-Body Neural Scene Flow", in International Conference on 3D Vision 2024.

31
/ 100
Emerging

This project helps computer vision researchers and robotics engineers evaluate advanced methods for understanding movement in 3D environments. It takes sequences of 3D point clouds, typically from LiDAR sensors on autonomous vehicles, and accurately estimates how objects and the scene are moving over time. The output is a highly precise measurement of scene flow and 4D trajectories, crucial for developing robust perception systems.

No commits in the last 6 months.

Use this if you are a researcher or engineer working on 3D scene understanding for autonomous systems and need to evaluate state-of-the-art methods for 3D scene flow and object trajectory estimation using real-world LiDAR data.

Not ideal if you are looking for a pre-trained, plug-and-play solution for general object tracking or if you don't have experience with deep learning research environments.

autonomous-driving 3D-perception robotics-navigation computer-vision-research LiDAR-data-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

14

Forks

2

Language

Python

License

MIT

Last pushed

Mar 11, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/kavisha725/MBNSF"

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