# Deep Floor Plan Recognition Using a Multi-Task Network with Room-Boundary-Guided Attention

arXiv: https://arxiv.org/abs/1908.11025 · HTML: https://mlsanity.com/paper/1908.11025/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Aug 2019.

## Built on by (most cited first, 27 of 27)

- [PedFormer: Pedestrian Behavior Prediction via Cross-Modal Attention Modulation and Gated Multitask Learning](https://mlsanity.com/paper/2210.07886/) (2022)
- [BIMgent: Towards Autonomous Building Modeling via Computer-use Agents](https://mlsanity.com/paper/2506.07217/) (2025)
- [Room Classification on Floor Plan Graphs using Graph Neural Networks](https://mlsanity.com/paper/2108.05947/) (2021)
- [Virtual Home Staging: Inverse Rendering and Editing an Indoor Panorama under Natural Illumination](https://mlsanity.com/paper/2311.12265/) (2023)
- [WAFFLE: Multimodal Floorplan Understanding in the Wild](https://mlsanity.com/paper/2412.00955/) (2024)
- [ArchCAD-400K: A Large-Scale CAD drawings Dataset and New Baseline for Panoptic Symbol Spotting](https://mlsanity.com/paper/2503.22346/) (2025)
- [Parsing Line Segments of Floor Plan Images Using Graph Neural Networks](https://mlsanity.com/paper/2303.03851/) (2023)
- [Automating Computational Design with Generative AI](https://mlsanity.com/paper/2307.02511/) (2023)
- [MuraNet: Multi-task Floor Plan Recognition with Relation Attention](https://mlsanity.com/paper/2309.00348/) (2023)
- [FloorGenT: Generative Vector Graphic Model of Floor Plans for Robotics](https://mlsanity.com/paper/2203.03385/) (2022)
- [VectorGraphNET: Graph Attention Networks for Accurate Segmentation of Complex Technical Drawings](https://mlsanity.com/paper/2410.01336/) (2024)
- [DoorDet: Semi-Automated Multi-Class Door Detection Dataset via Object Detection and Large Language Models](https://mlsanity.com/paper/2508.07714/) (2025)
- [Contrastive Diffusion Guidance for Spatial Inverse Problems](https://mlsanity.com/paper/2509.26489/) (2025)
- [Raster2Seq: Polygon Sequence Generation for Floorplan Reconstruction](https://mlsanity.com/paper/2602.09016/) (2026)
- [The scope for AI-augmented interpretation of building blueprints in commercial and industrial property insurance](https://mlsanity.com/paper/2205.01671/) (2022)
- [Offset-Guided Attention Network for Room-Level Aware Floor Plan Segmentation](https://mlsanity.com/paper/2210.17411/) (2022)
- [Towards Practical Multi-Robot Hybrid Tasks Allocation for Autonomous Cleaning](https://mlsanity.com/paper/2303.06531/) (2023)
- [Holistic Geometric Feature Learning for Structured Reconstruction](https://mlsanity.com/paper/2309.09622/) (2023)
- [Evaluating Panoramic 3D Estimation in Indoor Lighting Analysis](https://mlsanity.com/paper/2403.14836/) (2024)
- [Recognizing and Reconstructing a Multi-Unit Floor Plan](https://mlsanity.com/paper/2408.01526/) (2024)
- [SVG Decomposition for Enhancing Large Multimodal Models Visualization Comprehension: A Study with Floor Plans](https://mlsanity.com/paper/2511.03478/) (2025)
- [Enhancing Floor Plan Recognition: A Hybrid Mix-Transformer and U-Net Approach for Precise Wall Segmentation](https://mlsanity.com/paper/2512.02413/) (2025)
- [EasyControlEdge: A Foundation-Model Fine-Tuning for Edge Detection](https://mlsanity.com/paper/2602.16238/) (2026)
- [Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans](https://mlsanity.com/paper/2606.10953/) (2026)
- [Training-Free Agentic Computer Vision for Structural Component Detection in 2D Structural Framing Plans](https://mlsanity.com/paper/2608.17237/) (2026)
- [When Should a Network Emit Geometry, and When Should It Detect It? Readout, Reconciliation, and Representation in Floorplan Vectorization](https://mlsanity.com/paper/2608.25608/) (2026)
- [A Building as a Repository: KIR, a Typed Intermediate Representation for Agent-Authored Building Information Models](https://mlsanity.com/paper/2609.14578/) (2026)

## Abstract (arXiv)

This paper presents a new approach to recognize elements in floor plan layouts. Besides walls and rooms, we aim to recognize diverse floor plan elements, such as doors, windows and different types of rooms, in the floor layouts. To this end, we model a hierarchy of floor plan elements and design a deep multi-task neural network with two tasks: one to learn to predict room-boundary elements, and the other to predict rooms with types. More importantly, we formulate the room-boundary-guided attention mechanism in our spatial contextual module to carefully take room-boundary features into account to enhance the room-type predictions. Furthermore, we design a cross-and-within-task weighted loss to balance the multi-label tasks and prepare two new datasets for floor plan recognition. Experimental results demonstrate the superiority and effectiveness of our network over the state-of-the-art methods.