Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

MSD: A Benchmark Dataset for Floor Plan Generation of Building Complexes

Casper van Engelenburg, Fatemeh Mostafavi, Emanuel Kuhn, Yuntae Jeon, Michael Franzen, Matthias Standfest, Jan van Gemert, Seyran Khademi

TL;DR

This work introduces MSD, a large-scale European floor-plan dataset that targets realistic, multi-apartment building complexes to benchmark floor-plan generation. It formalizes a multi-modal generation task conditioned on building structure and a zoning graph, and provides both image and graph representations along with structural annotations. Two baselines, Modified HouseDiffusion (MHD) and Graph-informed U-Net (UN), expose substantial gaps between current state-of-the-art methods and the complexity of MSD, highlighting the need for graph- and boundary-aware approaches that can handle irregular geometries and inter-apartment connectivity. MSD, with its rich annotations and diverse topologies, enables rigorous evaluation via MIoU and graph compatibility, and is poised to drive future research in realistic floor-plan understanding and generation across European-building contexts.

Abstract

Diverse and realistic floor plan data are essential for the development of useful computer-aided methods in architectural design. Today's large-scale floor plan datasets predominantly feature simple floor plan layouts, typically representing single-apartment dwellings only. To compensate for the mismatch between current datasets and the real world, we develop \textbf{Modified Swiss Dwellings} (MSD) -- the first large-scale floor plan dataset that contains a significant share of layouts of multi-apartment dwellings. MSD features over 5.3K floor plans of medium- to large-scale building complexes, covering over 18.9K distinct apartments. We validate that existing approaches for floor plan generation, while effective in simpler scenarios, cannot yet seamlessly address the challenges posed by MSD. Our benchmark calls for new research in floor plan machine understanding. Code and data are open.

MSD: A Benchmark Dataset for Floor Plan Generation of Building Complexes

TL;DR

This work introduces MSD, a large-scale European floor-plan dataset that targets realistic, multi-apartment building complexes to benchmark floor-plan generation. It formalizes a multi-modal generation task conditioned on building structure and a zoning graph, and provides both image and graph representations along with structural annotations. Two baselines, Modified HouseDiffusion (MHD) and Graph-informed U-Net (UN), expose substantial gaps between current state-of-the-art methods and the complexity of MSD, highlighting the need for graph- and boundary-aware approaches that can handle irregular geometries and inter-apartment connectivity. MSD, with its rich annotations and diverse topologies, enables rigorous evaluation via MIoU and graph compatibility, and is poised to drive future research in realistic floor-plan understanding and generation across European-building contexts.

Abstract

Diverse and realistic floor plan data are essential for the development of useful computer-aided methods in architectural design. Today's large-scale floor plan datasets predominantly feature simple floor plan layouts, typically representing single-apartment dwellings only. To compensate for the mismatch between current datasets and the real world, we develop \textbf{Modified Swiss Dwellings} (MSD) -- the first large-scale floor plan dataset that contains a significant share of layouts of multi-apartment dwellings. MSD features over 5.3K floor plans of medium- to large-scale building complexes, covering over 18.9K distinct apartments. We validate that existing approaches for floor plan generation, while effective in simpler scenarios, cannot yet seamlessly address the challenges posed by MSD. Our benchmark calls for new research in floor plan machine understanding. Code and data are open.
Paper Structure (58 sections, 4 equations, 11 figures, 3 tables)

This paper contains 58 sections, 4 equations, 11 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. Floor plan datasets.
  4. Automated floor plan generation.
  5. Dataset of Modified Swiss Dwellings (MSD)
  6. Categorization & labeling.
  7. Image extraction.
  8. Graph extraction.
  9. Structure extraction.
  10. Comparison to other datasets
  11. Origin.
  12. Realism.
  13. Complexity.
  14. Information.
  15. Size & diversity.
  16. ...and 43 more sections

Figures (11)

  • Figure 1: MSD compared to RPLAN wu_data-driven_2019 and LIFULL lifull_co_ltd_lifull_nodate. Rooms are colored on function (e.g., blue for "bedroom"). The functional diagrams (represented as graphs) are drawn on top of the floor plans. MSD (right) significantly differs from RPLAN (left) and LIFULL (middle), as it contains more complex and realistic floor plans.
  • Figure 2: Representation of floor plan data. MSD contains three types of data. (Left) The floor plan is the complete layout of the floor of the building, including the position and shape of the rooms, doors, and windows. The areas are labeled by color (see legends). There are two category systems: 1) category is based on the type of the area ('room type'), in which each area has a room type (e.g., "bedroom"); and 2) category is based on the zone of the area ('zone type'), in which each areas has a zone type (e.g., "zone1"). (Middle) The associated room and zoning graphs are depicted on the right of the floor plans. The node colors are equivalent to the colors of the floor plan. The position of each node is taken as the centroid of the area that the node represents. (Right) A binary image of the necessary structural components of the floor plan.
  • Figure 3: Baseline methods for floor plan generation. (Left: UN) UN takes the building structure (image) as input to the U-Net. The U-Net is composed of an encoder and decoder using the conventional up- and down-sampling 2D convolutions, resp., and includes skip connections between the encoder and decoder feature maps at equivalent feature map scales. A GCN is used to map the zoning graph to a feature vector which is concatenated to the latent space of the U-Net. (Right: MHD) A wall encoder is used to map the pre-processed building structure into corresponding wall embeddings. MHD expands HD shabani_housediffusion_2023 by introducing an extra attention module (WCA) between the wall embeddings from and corner features of the rooms. A GAT is separately trained to predict the room types from the zoning types, which are used to "color" the full layout.
  • Figure 4: Example generations of MHD and UN. Columns 1 and 2 show the inputs: the zone graph and building structure respectively. Columns 3 - 6 show the floor plans generated by the MHD variants. Columns 7 - 9 show the floor plans generated by the UN variants. Column 10 shows the ground truth.
  • Figure 5: Area and unit distributions MSD. The unit distribution per floor (right), area distribution per floor (middle), and area distribution per unit (right) are plotted as histograms. The x-axis specifies the number of units or areas, and the y-axis specifies the frequency. From the unit distribution plot, it is apparent that MSD comprises mostly floor plans that contain between 2 to 9 units. MSD comprises mostly floor plans that have between 15 and 50 areas, with a peak of around 25. The area distribution per unit is similar to RPLAN wu_data-driven_2019 and LIFULL lifull_co_ltd_lifull_nodate, ranging between 3 and 15 areas per unit and a median around 7 areas per unit.
  • ...and 6 more figures