Published October 1, 2024 | Version v1

Floorplan Isovist Dataset

  • 1. ROR icon École Polytechnique Fédérale de Lausanne

Contributors

Supervisor:

  • 1. École Polytechnique Fédérale de Lausanne

Description

This dataset was created as part of the PhD project Machine Understanding of Architectural Space: From Analytical to Generative Applications at EPFL Media and Design Lab (LDM). It was derived from the Cubicasa5K dataset. The dataset contains preprocessed data and scripts to perform the transformation, sampling, and cleaning. This project explores machine learning techniques for understanding architectural spaces from isovist representation, ranging from analytical tasks such as spatial typification and semantic discovery to generative tasks such as spatial sequence synthesis. 
 

Files

floorplan_isovist_dataset.zip

Files (800.4 MB)

Name Size
md5:e28d3e55175b945073216aa804359add
800.4 MB Preview Download
md5:4fac9b9072ad060fe06640c22c98d768
3.4 kB Preview Download

Additional details

Software

Repository URL
https://github.com/johanesmikhael/isovist-machine-understanding
Programming language
Python
Development Status
Active