GregorKobsik/Octree-Transformer

Octree Transformer: Autoregressive 3D Shape Generation on Hierarchically Structured Sequences - CVPRW: StruCo3D, 2023

19
/ 100
Experimental

This project helps 3D artists, designers, and researchers automatically generate complex 3D shapes. You provide a dataset of existing 3D models, and the system learns to produce new, unique shapes with intricate details. It's ideal for anyone looking to create novel 3D content or expand existing 3D asset libraries.

No commits in the last 6 months.

Use this if you need to generate high-quality, complex 3D models from scratch without manual design, especially when working with large datasets of existing 3D shapes.

Not ideal if you need to precisely control every detail of the generated 3D shape or if you are only looking to edit existing models.

3D-modeling generative-design computer-graphics 3D-asset-creation shape-synthesis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

18

Forks

1

Language

Python

License

Last pushed

Jul 29, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/GregorKobsik/Octree-Transformer"

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