manycore-research/SpatialGen

[3DV 2026] SpatialGen: Layout-guided 3D Indoor Scene Generation

47
/ 100
Emerging

This project helps 3D artists, game developers, and interior designers rapidly create realistic 3D indoor scenes. You provide a 3D semantic layout (like a blueprint) and either a reference image or a textual description, and it generates a detailed 3D scene that matches your input. It's for professionals who need to visualize indoor spaces efficiently without building every detail from scratch.

360 stars.

Use this if you need to quickly generate detailed 3D indoor scenes from basic layouts, images, or text descriptions for design, visualization, or virtual environment creation.

Not ideal if you require highly precise, custom-modeled individual objects or outdoor environments, as its focus is on layout-guided indoor scene generation.

3D-design interior-design game-environment-creation architectural-visualization virtual-set-design
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 12 / 25

How are scores calculated?

Stars

360

Forks

19

Language

Python

License

MIT

Last pushed

Jan 27, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/manycore-research/SpatialGen"

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