WHU-USI3DV/FreeReg

[ICLR 2024] FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators

28
/ 100
Experimental

This tool helps 3D scanning and computer vision practitioners align a standard 2D image with a 3D point cloud of the same scene. You provide an image and a point cloud, and it outputs the precise spatial transformation needed to overlay them accurately. It's designed for professionals working with mixed 2D and 3D data who need to register them without manual intervention or extensive setup.

304 stars. No commits in the last 6 months.

Use this if you need to precisely align a 2D image with a 3D point cloud from a real-world scene, especially for mapping, robotics, or augmented reality applications.

Not ideal if your primary goal is 3D model creation from a single image or if you only work with 2D images or only 3D point clouds.

3D-scanning robotics augmented-reality spatial-mapping computer-vision
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 10 / 25

How are scores calculated?

Stars

304

Forks

13

Language

Python

License

Last pushed

Nov 25, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/WHU-USI3DV/FreeReg"

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