# Thinking Outside the Box: Generation of Unconstrained 3D Room Layouts

arXiv: https://arxiv.org/abs/1905.03105 · HTML: https://mlsanity.com/paper/1905.03105/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 May 2019.

## Built on by (most cited first, 10 of 10)

- [LaLaLoc: Latent Layout Localisation in Dynamic, Unvisited Environments](https://mlsanity.com/paper/2104.09169/) (2021)
- [MonteFloor: Extending MCTS for Reconstructing Accurate Large-Scale Floor Plans](https://mlsanity.com/paper/2103.11161/) (2021)
- [Building-GAN: Graph-Conditioned Architectural Volumetric Design Generation](https://mlsanity.com/paper/2104.13316/) (2021)
- [Learning to Reconstruct 3D Non-Cuboid Room Layout from a Single RGB Image](https://mlsanity.com/paper/2104.07986/) (2021)
- [Polygon Detection for Room Layout Estimation using Heterogeneous Graphs and Wireframes](https://mlsanity.com/paper/2306.12203/) (2023)
- [Semantic Room Wireframe Detection from a Single View](https://mlsanity.com/paper/2206.00491/) (2022)
- [MCTS with Refinement for Proposals Selection Games in Scene Understanding](https://mlsanity.com/paper/2207.03204/) (2022)
- [Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Model](https://mlsanity.com/paper/2502.16779/) (2025)
- [RoomStructNet: Learning to Rank Non-Cuboidal Room Layouts From Single View](https://mlsanity.com/paper/2110.00644/) (2021)
- [Ev-Layout: A Large-scale Event-based Multi-modal Dataset for Indoor Layout Estimation and Tracking](https://mlsanity.com/paper/2503.08370/) (2025)

## Abstract (arXiv)

We propose a method for room layout estimation that does not rely on the typical box approximation or Manhattan world assumption. Instead, we reformulate the geometry inference problem as an instance detection task, which we solve by directly regressing 3D planes using an R-CNN. We then use a variant of probabilistic clustering to combine the 3D planes regressed at each frame in a video sequence, with their respective camera poses, into a single global 3D room layout estimate. Finally, we showcase results which make no assumptions about perpendicular alignment, so can deal effectively with walls in any alignment.