# Automatic Generation of Constrained Furniture Layouts

arXiv: https://arxiv.org/abs/1711.10939 · HTML: https://mlsanity.com/paper/1711.10939/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2017.

## Built on by (most cited first, 8 of 8)

- [Variational Transformer Networks for Layout Generation](https://mlsanity.com/paper/2104.02416/) (2021)
- [Constrained Graphic Layout Generation via Latent Optimization](https://mlsanity.com/paper/2108.00871/) (2021)
- [SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation with Fine-Grained Geometry](https://mlsanity.com/paper/2302.10237/) (2023)
- [HSM: Hierarchical Scene Motifs for Multi-Scale Indoor Scene Generation](https://mlsanity.com/paper/2503.16848/) (2025)
- [Forest2Seq: Revitalizing Order Prior for Sequential Indoor Scene Synthesis](https://mlsanity.com/paper/2407.05388/) (2024)
- [Conditional 360-degree Image Synthesis for Immersive Indoor Scene Decoration](https://mlsanity.com/paper/2307.09621/) (2023)
- [Neural Scene Decoration from a Single Photograph](https://mlsanity.com/paper/2108.01806/) (2021)
- [PEARL: Parallelized Expert-Assisted Reinforcement Learning for Scene Rearrangement Planning](https://mlsanity.com/paper/2105.04088/) (2021)

## Abstract (arXiv)

Efficient authoring of vast virtual environments hinges on algorithms that are able to automatically generate content while also being controllable. We propose a method to automatically generate furniture layouts for indoor environments. Our method is simple, efficient, human-interpretable and amenable to a wide variety of constraints. We model the composition of rooms into classes of objects and learn joint (co-occurrence) statistics from a database of training layouts. We generate new layouts by performing a sequence of conditional sampling steps, exploiting the statistics learned from the database. The generated layouts are specified as 3D object models, along with their positions and orientations. We show they are of equivalent perceived quality to the training layouts, and compare favorably to a state-of-the-art method. We incorporate constraints using a general mechanism -- rejection sampling -- which provides great flexibility at the cost of extra computation. We demonstrate the versatility of our method by applying a wide variety of constraints relevant to real-world applications.