# Polygon Detection for Room Layout Estimation using Heterogeneous Graphs and Wireframes

arXiv: https://arxiv.org/abs/2306.12203 · HTML: https://mlsanity.com/paper/2306.12203/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 40 references that are in the map.
- First posted on arXiv 21 Jun 2023.

## Builds on (most cited first, 22 of 22)

- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [Heterogeneous Graph Transformer](https://mlsanity.com/paper/2003.01332/) (2020)
- [Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling](https://mlsanity.com/paper/1908.00222/) (2019)
- [PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image](https://mlsanity.com/paper/1812.04072/) (2018)
- [PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image](https://mlsanity.com/paper/1804.06278/) (2018)
- [End-to-End Wireframe Parsing](https://mlsanity.com/paper/1905.03246/) (2019)
- [Holistically-Attracted Wireframe Parsing](https://mlsanity.com/paper/2003.01663/) (2020)
- [Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding](https://mlsanity.com/paper/1902.09777/) (2019)
- [Learning Attraction Field Representation for Robust Line Segment Detection](https://mlsanity.com/paper/1812.02122/) (2018)
- [RoomNet: End-to-End Room Layout Estimation](https://mlsanity.com/paper/1703.06241/) (2017)
- [PlaneTR: Structure-Guided Transformers for 3D Plane Recovery](https://mlsanity.com/paper/2107.13108/) (2021)
- [Physics Inspired Optimization on Semantic Transfer Features: An Alternative Method for Room Layout Estimation](https://mlsanity.com/paper/1707.00383/) (2017)
- [General 3D Room Layout from a Single View by Render-and-Compare](https://mlsanity.com/paper/2001.02149/) (2020)
- [A Coarse-to-Fine Indoor Layout Estimation (CFILE) Method](https://mlsanity.com/paper/1607.00598/) (2016)
- [LGNN: A Context-aware Line Segment Detector](https://mlsanity.com/paper/2008.05892/) (2020)
- [Learning Regional Attraction for Line Segment Detection](https://mlsanity.com/paper/1912.09344/) (2019)
- [Thinking Outside the Box: Generation of Unconstrained 3D Room Layouts](https://mlsanity.com/paper/1905.03105/) (2019)
- [Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image](https://mlsanity.com/paper/2104.07986/) (2021)
- [Edge-Semantic Learning Strategy for Layout Estimation in Indoor Environment](https://mlsanity.com/paper/1901.00621/) (2019)
- [Semantic Room Wireframe Detection from a Single View](https://mlsanity.com/paper/2206.00491/) (2022)

## Built on by (most cited first, 6 of 6)

- [PolygonGNN: Representation Learning for Polygonal Geometries with Heterogeneous Visibility Graph](https://mlsanity.com/paper/2407.00742/) (2024)
- [Contrastive Diffusion Guidance for Spatial Inverse Problems](https://mlsanity.com/paper/2509.26489/) (2025)
- [The Impact of Semi-Supervised Learning on Line Segment Detection](https://mlsanity.com/paper/2411.04596/) (2024)
- [Ev-Layout: A Large-scale Event-based Multi-modal Dataset for Indoor Layout Estimation and Tracking](https://mlsanity.com/paper/2503.08370/) (2025)
- [Layout Anything: One Transformer for Universal Room Layout Estimation](https://mlsanity.com/paper/2512.02952/) (2025)
- [GALoc: Gravity Aligned Wireframes for Depth-Free Monocular Floorplan Localization](https://mlsanity.com/paper/2609.08385/) (2026)

## Abstract (arXiv)

This paper presents a neural network based semantic plane detection method utilizing polygon representations. The method can for example be used to solve room layout estimations tasks. The method is built on, combines and further develops several different modules from previous research. The network takes an RGB image and estimates a wireframe as well as a feature space using an hourglass backbone. From these, line and junction features are sampled. The lines and junctions are then represented as an undirected graph, from which polygon representations of the sought planes are obtained. Two different methods for this last step are investigated, where the most promising method is built on a heterogeneous graph transformer. The final output is in all cases a projection of the semantic planes in 2D. The methods are evaluated on the Structured 3D dataset and we investigate the performance both using sampled and estimated wireframes. The experiments show the potential of the graph-based method by outperforming state of the art methods in Room Layout estimation in the 2D metrics using synthetic wireframe detections.