# Convex Decomposition of Indoor Scenes

arXiv: https://arxiv.org/abs/2307.04246 · HTML: https://mlsanity.com/paper/2307.04246/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 68 references that are in the map.
- First posted on arXiv 9 Jul 2023.

## Builds on (most cited first, 28 of 28)

- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation](https://mlsanity.com/paper/1907.10326/) (2019)
- [What Do Single-view 3D Reconstruction Networks Learn?](https://mlsanity.com/paper/1905.03678/) (2019)
- [BSP-Net: Generating Compact Meshes via Binary Space Partitioning](https://mlsanity.com/paper/1911.06971/) (2019)
- [Learning Shape Abstractions by Assembling Volumetric Primitives](https://mlsanity.com/paper/1612.00404/) (2016)
- [CvxNet: Learnable Convex Decomposition](https://mlsanity.com/paper/1909.05736/) (2019)
- [Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids](https://mlsanity.com/paper/1904.09970/) (2019)
- [Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation](https://mlsanity.com/paper/2109.09881/) (2021)
- [PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image](https://mlsanity.com/paper/1812.04072/) (2018)
- [LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image](https://mlsanity.com/paper/1803.08999/) (2018)
- [Supervised Fitting of Geometric Primitives to 3D Point Clouds](https://mlsanity.com/paper/1811.08988/) (2018)
- [3D-PRNN: Generating Shape Primitives with Recurrent Neural Networks](https://mlsanity.com/paper/1708.01648/) (2017)
- [PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image](https://mlsanity.com/paper/1804.06278/) (2018)
- [ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation](https://mlsanity.com/paper/2108.10528/) (2021)
- [Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Search](https://mlsanity.com/paper/2205.02961/) (2022)
- [Designing Deep Networks for Surface Normal Estimation](https://mlsanity.com/paper/1411.4958/) (2014)
- [Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes](https://mlsanity.com/paper/2207.08656/) (2022)
- [Deep Parametric Shape Predictions using Distance Fields](https://mlsanity.com/paper/1904.08921/) (2019)
- [Learning Generative Models of Shape Handles](https://mlsanity.com/paper/2004.03028/) (2020)
- [General 3D Room Layout from a Single View by Render-and-Compare](https://mlsanity.com/paper/2001.02149/) (2020)
- [Monte Carlo Scene Search for 3D Scene Understanding](https://mlsanity.com/paper/2103.07969/) (2021)
- [Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images](https://mlsanity.com/paper/2105.02047/) (2021)
- [MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud](https://mlsanity.com/paper/2207.14268/) (2022)
- [LSD-StructureNet: Modeling Levels of Structural Detail in 3D Part Hierarchies](https://mlsanity.com/paper/2108.13459/) (2021)
- [Cerberus: A Multi-headed Derenderer](https://mlsanity.com/paper/1905.11940/) (2019)
- [Blocks2World: Controlling Realistic Scenes with Editable Primitives](https://mlsanity.com/paper/2307.03847/) (2023)

## Built on by (most cited first, 7 of 7)

- [Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting](https://mlsanity.com/paper/2503.21770/) (2025)
- [Robust Shape Fitting for 3D Scene Abstraction](https://mlsanity.com/paper/2403.10452/) (2024)
- [Denoising Monte Carlo Renders with Diffusion Models](https://mlsanity.com/paper/2404.00491/) (2024)
- [Generative Blocks World: Moving Things Around in Pictures](https://mlsanity.com/paper/2506.20703/) (2025)
- [Improved Convex Decomposition with Ensembling and Negative Primitives](https://mlsanity.com/paper/2405.19569/) (2024)
- [PrITTI: Primitive-based Generation of Controllable and Editable 3D Semantic Urban Scenes](https://mlsanity.com/paper/2506.19117/) (2025)
- [I2CD: Direct Image-to-Convex Decomposition for Simulation-Ready Collision Geometry](https://mlsanity.com/paper/2610.03453/) (2026)

## Abstract (arXiv)

We describe a method to parse a complex, cluttered indoor scene into primitives which offer a parsimonious abstraction of scene structure. Our primitives are simple convexes. Our method uses a learned regression procedure to parse a scene into a fixed number of convexes from RGBD input, and can optionally accept segmentations to improve the decomposition. The result is then polished with a descent method which adjusts the convexes to produce a very good fit, and greedily removes superfluous primitives. Because the entire scene is parsed, we can evaluate using traditional depth, normal, and segmentation error metrics. Our evaluation procedure demonstrates that the error from our primitive representation is comparable to that of predicting depth from a single image.