marian42/shapegan

Generative Adversarial Networks and Autoencoders for 3D Shapes

39
/ 100
Emerging

This project helps designers and researchers working with 3D models to generate new shapes or reconstruct existing ones. You provide a collection of 3D mesh files (like a database of chairs or airplanes), and it outputs new, unique 3D shapes or detailed reconstructions from a compressed representation. It's for anyone in fields like industrial design, game development, or scientific visualization who needs to expand a dataset of 3D objects or analyze shape variations.

327 stars. No commits in the last 6 months.

Use this if you need to automatically generate novel 3D object designs based on a dataset of existing shapes or if you want to create highly detailed 3D reconstructions from efficient data representations.

Not ideal if you're looking for a simple drag-and-drop tool for occasional 3D model manipulation or if you don't have access to powerful computing resources, specifically a datacenter-grade GPU.

3D-modeling generative-design product-development computer-graphics shape-analysis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 21 / 25

How are scores calculated?

Stars

327

Forks

57

Language

Python

License

Last pushed

Oct 09, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/marian42/shapegan"

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