astaka-pe/Dual-DMP

Learning Self-prior for Mesh Denoising using Dual Graph Convolutional Networks [ECCV 2022]

28
/ 100
Experimental

This tool helps 3D designers and engineers clean up noisy 3D mesh models, which often result from 3D scanning or CAD modeling errors. You provide a noisy 3D mesh file (e.g., an OBJ file) as input, and it outputs a much smoother, denoised version of the same 3D model. This is ideal for anyone working with digital twins, 3D printing, or virtual reality who needs high-quality, artifact-free 3D geometries.

No commits in the last 6 months.

Use this if you need to automatically remove imperfections and noise from a single 3D mesh model to improve its visual quality or prepare it for manufacturing.

Not ideal if you need to reconstruct a 3D model from point clouds or perform complex mesh repair beyond simple denoising.

3D-modeling CAD 3D-scanning digital-manufacturing virtual-reality
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 10 / 25

How are scores calculated?

Stars

44

Forks

4

Language

Python

License

Last pushed

Apr 13, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/astaka-pe/Dual-DMP"

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