jbji/RepVF

[ECCV 2024] Official implementation for "RepVF: A Unified Vector Fields Representation for Multi-task 3D Perception"

32
/ 100
Emerging

This project helps self-driving car engineers and researchers efficiently develop autonomous driving systems. It takes raw 3D scene data (like from LiDAR or cameras) and processes it to simultaneously identify multiple critical elements, such as objects and lane boundaries. The result is a unified, computationally efficient understanding of the vehicle's surroundings, reducing conflicts and improving overall perception for autonomous vehicles.

No commits in the last 6 months.

Use this if you are developing or researching multi-task 3D perception systems for autonomous driving and need to process different scene understanding tasks simultaneously and efficiently.

Not ideal if your work focuses on single-task 3D perception or if you are not working within the autonomous driving domain.

autonomous-driving 3D-perception multi-task-learning vehicle-vision robotics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

33

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Mar 27, 2025

Commits (30d)

0

Get this data via API

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

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