Adapting HouseDiffusion for conditional Floor Plan generation on Modified Swiss Dwellings dataset
This work addresses automated floor plan generation for architectural design, but it is incremental as it adapts an existing method to a new dataset with minor modifications.
The authors tackled the problem of conditional floor plan generation by adapting HouseDiffusion to the Modified Swiss Dwellings dataset, which includes structural walls as constraints, and found that simplifying room polygons to rectangles improved performance.
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.