aminshabani/house_diffusion

The implementation of "HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with Discrete and Continuous Denoising", https://arxiv.org/abs/2211.13287

41
/ 100
Emerging

Hybrid denoising approach that handles both discrete room types and continuous geometric coordinates simultaneously for vector-based floorplan synthesis. Built on OpenAI's guided-diffusion framework and trained on the RPLAN dataset with preprocessing from House-GAN++. Supports end-to-end training and sampling workflows with configurable batch sizes and model checkpoints.

212 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 22 / 25

How are scores calculated?

Stars

212

Forks

51

Language

Python

License

Last pushed

Aug 30, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/aminshabani/house_diffusion"

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