csiro-robotics/Reg-NF

[ICRA 2024] Official repository of Reg-NF: Efficient Registration of Implicit Surfaces within Neural Fields

20
/ 100
Experimental

This tool helps robotics engineers or researchers precisely align 3D models of objects, known as neural fields, with larger 3D scene models. You input two 3D neural field models – one for an object and one for a scene – and it outputs the exact 3D position and orientation needed to place the object within the scene. This is ideal for tasks like robotic manipulation, scene reconstruction, or simulating object placement in a virtual environment.

No commits in the last 6 months.

Use this if you need to accurately determine the 6-degree-of-freedom transformation (position and rotation) between a 3D object model and a 3D scene model, both represented as neural fields.

Not ideal if your 3D models are represented as traditional point clouds or meshes, as this tool specifically works with implicit neural field representations.

robotics 3D-scene-understanding object-pose-estimation computer-vision augmented-reality
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Python

License

Last pushed

Sep 24, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/csiro-robotics/Reg-NF"

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