# GRAINS: Generative Recursive Autoencoders for INdoor Scenes

arXiv: https://arxiv.org/abs/1807.09193 · HTML: https://mlsanity.com/paper/1807.09193/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jul 2018.

## Built on by (most cited first, 30 of 38)

- [ATISS: Autoregressive Transformers for Indoor Scene Synthesis](https://mlsanity.com/paper/2110.03675/) (2021)
- [Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes Using Scene Graphs](https://mlsanity.com/paper/2108.08841/) (2021)
- [LEGO-Net: Learning Regular Rearrangements of Objects in Rooms](https://mlsanity.com/paper/2301.09629/) (2023)
- [MIME: Human-Aware 3D Scene Generation](https://mlsanity.com/paper/2212.04360/) (2022)
- [Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis](https://mlsanity.com/paper/2103.05558/) (2021)
- [RGBD2: Generative Scene Synthesis via Incremental View Inpainting using RGBD Diffusion Models](https://mlsanity.com/paper/2212.05993/) (2022)
- [Mixed Diffusion for 3D Indoor Scene Synthesis](https://mlsanity.com/paper/2405.21066/) (2024)
- [SPAGHETTI: Editing Implicit Shapes Through Part Aware Generation](https://mlsanity.com/paper/2201.13168/) (2022)
- [Indoor Scene Generation from a Collection of Semantic-Segmented Depth Images](https://mlsanity.com/paper/2108.09022/) (2021)
- [SceneEval: Evaluating Semantic Coherence in Text-Conditioned 3D Indoor Scene Synthesis](https://mlsanity.com/paper/2503.14756/) (2025)
- [Learning 3D Scene Priors with 2D Supervision](https://mlsanity.com/paper/2211.14157/) (2022)
- [SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation](https://mlsanity.com/paper/2412.01801/) (2024)
- [HSM: Hierarchical Scene Motifs for Multi-Scale Indoor Scene Generation](https://mlsanity.com/paper/2503.16848/) (2025)
- [3D Scene Generation: A Survey](https://mlsanity.com/paper/2505.05474/) (2025)
- [SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstruction](https://mlsanity.com/paper/2309.15702/) (2023)
- [LayoutEnhancer: Generating Good Indoor Layouts from Imperfect Data](https://mlsanity.com/paper/2202.00185/) (2022)
- [Patch-based 3D Natural Scene Generation from a Single Example](https://mlsanity.com/paper/2304.12670/) (2023)
- [CasaGPT: Cuboid Arrangement and Scene Assembly for Interior Design](https://mlsanity.com/paper/2504.19478/) (2025)
- [FurniScene: A Large-scale 3D Room Dataset with Intricate Furnishing Scenes](https://mlsanity.com/paper/2401.03470/) (2024)
- [Spatial Commonsense Graph for Object Localisation in Partial Scenes](https://mlsanity.com/paper/2203.05380/) (2022)
- [Diverse Multimedia Layout Generation with Multi Choice Learning](https://mlsanity.com/paper/2301.06629/) (2023)
- [SemIE: Semantically-aware Image Extrapolation](https://mlsanity.com/paper/2108.13702/) (2021)
- [SemLayoutDiff: Semantic Layout Generation with Diffusion Model for Indoor Scene Synthesis](https://mlsanity.com/paper/2508.18597/) (2025)
- [Walk2Map: Extracting Floor Plans from Indoor Walk Trajectories](https://mlsanity.com/paper/2103.00262/) (2021)
- [AutoEncoding Tree for City Generation and Applications](https://mlsanity.com/paper/2309.15941/) (2023)
- [In-game Residential Home Planning via Visual Context-aware Global Relation Learning](https://mlsanity.com/paper/2102.04035/) (2021)
- [Contextual Scene Augmentation and Synthesis via GSACNet](https://mlsanity.com/paper/2103.15369/) (2021)
- [ReGroup: Recursive Neural Networks for Hierarchical Grouping of Vector Graphic Primitives](https://mlsanity.com/paper/2111.11759/) (2021)
- [Learning to Place Objects with Programs and Iterative Self Training](https://mlsanity.com/paper/2503.04496/) (2025)
- [Deep Reinforcement Learning for Producing Furniture Layout in Indoor Scenes](https://mlsanity.com/paper/2101.07462/) (2021)

## Abstract (arXiv)

We present a generative neural network which enables us to generate plausible 3D indoor scenes in large quantities and varieties, easily and highly efficiently. Our key observation is that indoor scene structures are inherently hierarchical. Hence, our network is not convolutional; it is a recursive neural network or RvNN. Using a dataset of annotated scene hierarchies, we train a variational recursive autoencoder, or RvNN-VAE, which performs scene object grouping during its encoding phase and scene generation during decoding. Specifically, a set of encoders are recursively applied to group 3D objects based on support, surround, and co-occurrence relations in a scene, encoding information about object spatial properties, semantics, and their relative positioning with respect to other objects in the hierarchy. By training a variational autoencoder (VAE), the resulting fixed-length codes roughly follow a Gaussian distribution. A novel 3D scene can be generated hierarchically by the decoder from a randomly sampled code from the learned distribution. We coin our method GRAINS, for Generative Recursive Autoencoders for INdoor Scenes. We demonstrate the capability of GRAINS to generate plausible and diverse 3D indoor scenes and compare with existing methods for 3D scene synthesis. We show applications of GRAINS including 3D scene modeling from 2D layouts, scene editing, and semantic scene segmentation via PointNet whose performance is boosted by the large quantity and variety of 3D scenes generated by our method.