raphaelsulzer/dgnn

[SGP 2021] Scalable Surface Reconstruction with Delaunay-Graph Neural Networks

35
/ 100
Emerging

This project helps create detailed 3D models from raw 3D scan data, which often contains only scattered points. It takes in point clouds—essentially a collection of 3D coordinates representing an object's surface—and outputs a clean, continuous 3D mesh. This is ideal for 3D artists, computer graphics professionals, and researchers working with scanned objects or environments who need a complete digital surface.

No commits in the last 6 months.

Use this if you need to reliably convert noisy or incomplete 3D point cloud data into a smooth, high-quality 3D surface mesh for visualization, analysis, or further processing.

Not ideal if you're looking for a simple click-and-drag 3D modeling software, as this tool requires some technical setup and command-line execution.

3D-reconstruction computer-graphics 3D-scanning mesh-generation digital-archaeology
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

42

Forks

5

Language

Python

License

MIT

Last pushed

Mar 14, 2025

Commits (30d)

0

Get this data via API

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

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