Modified Swiss Dwellings: a Machine Learning-ready Dataset for Floor Plan Auto-Completion at Scale

doi: 10.4121/e1d89cb5-6872-48fc-be63-aadd687ee6f9.v2
The doi above is for this specific version of this dataset, which is currently the latest. Newer versions may be published in the future. For a link that will always point to the latest version, please use
doi: 10.4121/e1d89cb5-6872-48fc-be63-aadd687ee6f9
Datacite citation style:
van Engelenburg, Casper; Khademi, Seyran; Mostafavi, Fatemeh; Standfest, Matthias; Franzen, Michael (2023): Modified Swiss Dwellings: a Machine Learning-ready Dataset for Floor Plan Auto-Completion at Scale . Version 2. 4TU.ResearchData. dataset. https://doi.org/10.4121/e1d89cb5-6872-48fc-be63-aadd687ee6f9.v2
Other citation styles (APA, Harvard, MLA, Vancouver, Chicago, IEEE) available at Datacite
Dataset
choose version:
version 2 - 2023-07-11 (latest)
version 1 - 2023-06-23

Modified Swiss Dwellings

The Modified Swiss Dwellings (MSD) dataset is a machine learning-ready dataset for floor plan auto-completion at scale. The MSD dataset is derived from the Swiss Dwellings database (v3.0.0). The MSD dataset (train split) contains 4167 floor plans of single- as well as multi-unit building complexes across Switzerland, hence extending the building scale w.r.t. of other well know floor plan datasets like the RPLAN dataset. Since the MSD dataset will be part of a challenge @ ICCV in Paris, 2023, October 3, the test split is not yet made public. This will be added after the submission deadline of the challenge, which will be around mid September 2023.


Cleaning, filtering, and processing

All cleaning, filtering, and processing is done in Python. The Swiss Dwellings database is cleaned and filtered on residential building complexes that have a minimum room count (>10) and have at least 2 "Zone 2" rooms (e.g., living room, corridor, kitchen, dining). A graph extraction algorithm fully based on the `shapely` and `networkx` libraries in Python was developed to extract the access graphs from the filtered floor plans.


Dataset structure

The MSD dataset contains 3 files.


1) A README.md file explaining the dataset.

2) A training set ZIP archive, containing 4 folders: `graph_in` [<index>.pickle], `struct_in` [<index>.npy], `full_out` [<index>.npy], and `graph_out` [<index>.pickle]. Naming is consistent across all folders, meaning that an instance from `graph_in` with name "<index>.pickle" is from the same floor plan as an instance from `full_out` with name "<index>.npy".

3) A test set ZIP archive, containing 2 folders: `graph_in` and `struct_in` (similarly structured as the training data; but obviously with withheld annotations.)


Floor plan auto-completion

The MSD dataset is developed with the goal for the computer science community to develop (deep learning) models for the task of floor plan auto-completion. The floor plan auto-completion task takes as input the boundary of a building, the structural elements necessary for the building’s structural integrity, and a set of user constraints formalized in a graph structure, with the goal of automatically generating the full floor plan. Specifically, the goal is to learn the correlation between the the joint distribution of `graph_in` and `struct_in` with that of `full_out`. `graph_out` is provided when researchers want to use / develop methods from graph signal processing, or graph machine learning specifically.


GIthub guidelines

Github page.

history
  • 2023-06-23 first online
  • 2023-07-11 published, posted
publisher
4TU.ResearchData
format
zip of folders; containing .pickle and .npy files
organizations
TU Delft, Faculty of Architecture and Built Environment, Department of Architecture;
Archylise A.G

DATA

files (3)