Adapting HouseDiffusion for conditional Floor Plan generation on Modified Swiss Dwellings dataset

TL;DR

This paper extends HouseDiffusion for conditional floor plan generation on the MSD dataset by incorporating structural wall constraints through model modifications and preprocessing techniques.

Contribution

It introduces a method to adapt HouseDiffusion for structural constraints using wall line conditioning and polygon simplification.

Findings

Wall line conditioning improves generation accuracy

Polygon simplification enhances model performance

Future work needed on variable-length polygon representations

Abstract

Automated floor plan generation has recently gained momentum with several methods that have been proposed. The CVAAD Floor Plan Auto-Completion workshop challenge introduced MSD, a new dataset that includes existing structural walls of the building as an additional input constraint. This technical report presents an approach for extending a recent work, HouseDiffusion (arXiv:2211.13287 [cs.CV]), to the MSD dataset. The adaption involves modifying the model's transformer layers to condition on a set of wall lines. The report introduces a pre-processing pipeline to extract wall lines from the binary mask of the building structure provided as input. Additionally, it was found that a data processing procedure that simplifies all room polygons to rectangles leads to better performance. This indicates that future work should explore better representations of variable-length polygons in diffusion models. The code will be made available at a later date.