mabaorui/NeuralPull-Pytorch

Implementation of ICML'2021:Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces

31
/ 100
Emerging

This project helps convert messy 3D point cloud data into clean, usable 3D surface models. It takes raw scans of objects or environments as input and outputs a smooth, reconstructed mesh that accurately represents the original shape. This tool is ideal for 3D artists, designers, engineers, or researchers working with scanned physical objects.

No commits in the last 6 months.

Use this if you need to create a solid, watertight 3D model from unorganized 3D scan data (point clouds).

Not ideal if you're looking for a tool to generate 3D models from scratch using traditional modeling techniques or descriptive parameters.

3D-reconstruction reverse-engineering computer-graphics digital-archiving 3D-scanning
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

79

Forks

11

Language

Python

License

Last pushed

Feb 04, 2024

Commits (30d)

0

Get this data via API

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

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