I read “Automatic Reconstruction of Semantic 3D Models from 2D Floor Plans” by Cambeiro Barreiro et al. (2023). The goal they had was to turn scanned plans into vector 3D models that you can export as IFC, a building data format. It lets different BIM (Building Information Modeling) tools share the same data, like walls, rooms, and doors, etc. This matters especially for big real estate portfolio holders, like housing associations. These parties would be able to gather insights from the vast amounts of data, which are normally only available on paper.
The core problem
Symbols and techniques differ, and old drawings are clumsy. Windows and doors break through walls. The scans are biased. Redrawing by hand is labour-intensive, expensive, and error-prone. The stakes are higher for large portfolio holders, such as housing associations. They oversee thousands of residences. They are unable to compare layouts, energy features, or risks across the stock in the absence of structured data.
How it actually works
You begin with floor plan scans or PDFs. Like a human, the system reads the plan. It recognises windows, doors, and walls. It corrects gaps and crooked lines. After that, it creates clean vectors from these shapes. Lastly, it exports IFC and creates a basic 3D model. Common BIM tools can use that file. You can then measure areas, tag units, and count rooms. Additionally, you can link maintenance notes or energy data. Structure is crucial. You can perform the same checks on buildings in the portfolio at large scale once the data is in a standardised format.
source: Cambeiro Barreiro et al., 2023
Why portfolio owners should care
Data is locked in drawers by paper plans. They become structured BIM thanks to this pipeline. This opens up the portfolio’s unit mix, wall types, window counts, and layout features. It facilitates large-scale renovation planning, accessibility assessments, and energy audits. You receive a cleaner handoff to designers and contractors and expedited due diligence.
Takeaway
Digitising plans is the first step if you own a sizeable housing portfolio and would like to digitize. Segment walls, identify symbols, and carefully translate everything using floor-plan AI. To prevent lock-in and maintain the data’s utility across tools, export to a common data type like IFC. The improvements are easy to understand in terms of speed, consistency, and insight at the portfolio level.
Reference: Cambeiro Barreiro, A., Trzeciakiewicz, M., Hilsmann, A., & Eisert, P. (2023). Automatic Reconstruction of Semantic 3D Models from 2D Floor Plans.
