tangjiapeng/DiffuScene

[CVPR 2024] DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis

42
/ 100
Emerging

This project helps interior designers, architects, and 3D artists quickly create realistic indoor scene layouts. You can input existing room designs, a few objects, or a text description, and it generates diverse, well-arranged 3D indoor scenes with objects like furniture. This is for professionals who need to visualize or generate many scene variations efficiently.

331 stars. No commits in the last 6 months.

Use this if you need to rapidly generate or complete high-quality 3D indoor scenes from partial information or text descriptions, without manually placing every object.

Not ideal if you require extremely precise, hand-tuned placement of every single object with specific custom models not present in the underlying datasets.

interior-design 3d-modeling architectural-visualization scene-generation virtual-staging
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

331

Forks

35

Language

Python

License

Last pushed

Apr 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/tangjiapeng/DiffuScene"

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