csiro-robotics/Reg-NF
[ICRA 2024] Official repository of Reg-NF: Efficient Registration of Implicit Surfaces within Neural Fields
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.
Stars
8
Forks
—
Language
Python
License
—
Category
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.
Higher-rated alternatives
NVlabs/instant-ngp
Instant neural graphics primitives: lightning fast NeRF and more
nerfstudio-project/nerfstudio
A collaboration friendly studio for NeRFs
google/nerfies
This is the code for Deformable Neural Radiance Fields, a.k.a. Nerfies.
SuLvXiangXin/zipnerf-pytorch
Unofficial implementation of ZipNeRF
yashbhalgat/HashNeRF-pytorch
Pure PyTorch Implementation of NVIDIA paper on Instant Training of Neural Graphics primitives:...