%0 Generic %A van Engelenburg, Casper %A Khademi, Seyran %A Mostafavi, Fatemeh %A Standfest, Matthias %A Franzen, Michael %D 2023 %T Modified Swiss Dwellings: a Machine Learning-ready Dataset for Floor Plan Auto-Completion at Scale %U %R 10.4121/e1d89cb5-6872-48fc-be63-aadd687ee6f9.v2 %K floor plan generation %K floor plan auto-completion %K computer vision %K graph machine learning %K access graph %K functional graph %X <p><em>Modified Swiss Dwellings</em></p><p>The Modified Swiss Dwellings (MSD) dataset is a <strong>machine learning-ready dataset for floor plan auto-completion at scale</strong>. The MSD dataset is derived from the <a href="https://zenodo.org/record/7788422" target="_blank">Swiss Dwellings database</a> (v3.0.0). The MSD dataset (train split) contains <strong>4167 floor plans</strong> of <strong>single- as well as multi-unit building complexes across Switzerland</strong>, hence extending the building scale w.r.t. of other well know floor plan datasets like the <a href="http://staff.ustc.edu.cn/~fuxm/projects/DeepLayout/index.html" target="_blank">RPLAN</a> dataset. Since the MSD dataset will be part of a challenge @ ICCV in Paris, 2023, October 3, the <strong>test split is not yet made public</strong>. This will be added after the submission deadline of the challenge, which will be around mid September 2023.</p><p></p><p><em>Cleaning, filtering, and processing</em></p><p>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 (<em>e.g.</em>, 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.</p><p></p><p><em>Dataset structure</em></p><p>The MSD dataset contains 3 files.</p><p></p><p>1) A README.md file explaining the dataset.</p><p>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".</p><p>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.)</p><p></p><p><em>Floor plan auto-completion</em></p><p>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.</p><p></p><p><em>GIthub guidelines</em></p><p><a href="https://github.com/cvaad-workshop/iccv23-challenge.git" target="_blank">Github page</a>.</p> %I 4TU.ResearchData