# Structured Graph Variational Autoencoders for Indoor Furniture layout Generation

arXiv: https://arxiv.org/abs/2204.04867 · HTML: https://mlsanity.com/paper/2204.04867/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 38 references that are in the map.
- First posted on arXiv 11 Apr 2022.

## Builds on (most cited first, 26 of 26)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Semi-Supervised Learning with Deep Generative Models](https://mlsanity.com/paper/1406.5298/) (2014)
- [GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders](https://mlsanity.com/paper/1802.03480/) (2018)
- [3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics](https://mlsanity.com/paper/2011.09127/) (2020)
- [Grammar Variational Autoencoder](https://mlsanity.com/paper/1703.01925/) (2017)
- [3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera](https://mlsanity.com/paper/1910.02527/) (2019)
- [VAE with a VampPrior](https://mlsanity.com/paper/1705.07120/) (2017)
- [Variational Inference of Disentangled Latent Concepts from Unlabeled Observations](https://mlsanity.com/paper/1711.00848/) (2017)
- [ATISS: Autoregressive Transformers for Indoor Scene Synthesis](https://mlsanity.com/paper/2110.03675/) (2021)
- [Variational Lossy Autoencoder](https://mlsanity.com/paper/1611.02731/) (2016)
- [SceneFormer: Indoor Scene Generation with Transformers](https://mlsanity.com/paper/2012.09793/) (2020)
- [Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models](https://mlsanity.com/paper/1811.12463/) (2018)
- [Human-centric Indoor Scene Synthesis Using Stochastic Grammar](https://mlsanity.com/paper/1808.08473/) (2018)
- [Deep Generative Modeling for Scene Synthesis via Hybrid Representations](https://mlsanity.com/paper/1808.02084/) (2018)
- [Learning Hierarchical Priors in VAEs](https://mlsanity.com/paper/1905.04982/) (2019)
- [End-to-End Optimization of Scene Layout](https://mlsanity.com/paper/2007.11744/) (2020)
- [Probably Approximately Correct Constrained Learning](https://mlsanity.com/paper/2006.05487/) (2020)
- [Generative Layout Modeling using Constraint Graphs](https://mlsanity.com/paper/2011.13417/) (2020)
- [GRAINS: Generative Recursive Autoencoders for INdoor Scenes](https://mlsanity.com/paper/1807.09193/) (2018)
- [Configurable 3D Scene Synthesis and 2D Image Rendering with Per-Pixel Ground Truth using Stochastic Grammars](https://mlsanity.com/paper/1704.00112/) (2017)
- [SceneGen: Generative Contextual Scene Augmentation using Scene Graph Priors](https://mlsanity.com/paper/2009.12395/) (2020)

## Built on by (most cited first, 1 of 1)

- [ProcTHOR: Large-Scale Embodied AI Using Procedural Generation](https://mlsanity.com/paper/2206.06994/) (2022)

## Abstract (arXiv)

We present a structured graph variational autoencoder for generating the layout of indoor 3D scenes. Given the room type (e.g., living room or library) and the room layout (e.g., room elements such as floor and walls), our architecture generates a collection of objects (e.g., furniture items such as sofa, table and chairs) that is consistent with the room type and layout. This is a challenging problem because the generated scene should satisfy multiple constrains, e.g., each object must lie inside the room and two objects cannot occupy the same volume. To address these challenges, we propose a deep generative model that encodes these relationships as soft constraints on an attributed graph (e.g., the nodes capture attributes of room and furniture elements, such as class, pose and size, and the edges capture geometric relationships such as relative orientation). The architecture consists of a graph encoder that maps the input graph to a structured latent space, and a graph decoder that generates a furniture graph, given a latent code and the room graph. The latent space is modeled with auto-regressive priors, which facilitates the generation of highly structured scenes. We also propose an efficient training procedure that combines matching and constrained learning. Experiments on the 3D-FRONT dataset show that our method produces scenes that are diverse and are adapted to the room layout.