mabaorui/Noise2NoiseMapping

[ICML'23 Oral] Learning Signed Distance Functions from Noisy 3D Point Clouds via Noise to Noise Mapping

28
/ 100
Experimental

This helps researchers and engineers working with 3D models to improve the quality of 3D reconstructions from imperfect sensor data. It takes in 3D point cloud data that might have errors or noise and produces a cleaner, more accurate signed distance function (SDF) representation. This tool is for anyone who needs to convert raw, noisy 3D scans into smooth, mathematically defined surfaces for tasks like CAD modeling or simulation.

125 stars. No commits in the last 6 months.

Use this if you need to accurately reconstruct smooth 3D surfaces from noisy point cloud scans obtained from sensors like LiDAR or 3D scanners.

Not ideal if your input data is already perfectly clean or if you are working with 2D images instead of 3D point clouds.

3D-reconstruction point-cloud-processing computer-vision geometric-modeling digital-twin
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

125

Forks

8

Language

Python

License

Last pushed

Aug 21, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mabaorui/Noise2NoiseMapping"

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