English

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

Computer Vision and Pattern Recognition 2023-12-08 v1

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.

Keywords

Cite

@article{arxiv.2312.03938,
  title  = {Adapting HouseDiffusion for conditional Floor Plan generation on Modified Swiss Dwellings dataset},
  author = {Emanuel Kuhn},
  journal= {arXiv preprint arXiv:2312.03938},
  year   = {2023}
}