# Improved Convex Decomposition with Ensembling and Negative Primitives

arXiv: https://arxiv.org/abs/2405.19569 · HTML: https://mlsanity.com/paper/2405.19569/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 79 references that are in the map.
- First posted on arXiv 29 May 2024.

## Builds on (most cited first, 30 of 38)

- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding](https://mlsanity.com/paper/2011.02523/) (2020)
- [DeepCAD: A Deep Generative Network for Computer-Aided Design Models](https://mlsanity.com/paper/2105.09492/) (2021)
- [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)
- [Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids](https://mlsanity.com/paper/1904.09970/) (2019)
- [PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image](https://mlsanity.com/paper/1812.04072/) (2018)
- [Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks](https://mlsanity.com/paper/2103.10429/) (2021)
- [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)
- [LooseControl: Lifting ControlNet for Generalized Depth Conditioning](https://mlsanity.com/paper/2312.03079/) (2023)
- [Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Search](https://mlsanity.com/paper/2205.02961/) (2022)
- [CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assembly](https://mlsanity.com/paper/2104.05652/) (2021)
- [Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinders](https://mlsanity.com/paper/2112.09329/) (2021)
- [Designing Deep Networks for Surface Normal Estimation](https://mlsanity.com/paper/1411.4958/) (2014)
- [StructureNet: Hierarchical Graph Networks for 3D Shape Generation](https://mlsanity.com/paper/1908.00575/) (2019)
- [Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes](https://mlsanity.com/paper/2207.08656/) (2022)
- [Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives](https://mlsanity.com/paper/2307.05473/) (2023)
- [Deep Parametric Shape Predictions using Distance Fields](https://mlsanity.com/paper/1904.08921/) (2019)
- [CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus](https://mlsanity.com/paper/2001.02643/) (2020)
- [SPAGHETTI: Editing Implicit Shapes Through Part Aware Generation](https://mlsanity.com/paper/2201.13168/) (2022)
- [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)

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

- [I2CD: Direct Image-to-Convex Decomposition for Simulation-Ready Collision Geometry](https://mlsanity.com/paper/2610.03453/) (2026)

## Abstract (arXiv)

Describing a scene in terms of primitives -- geometrically simple shapes that offer a parsimonious but accurate abstraction of structure -- is an established and difficult fitting problem. Different scenes require different numbers of primitives, and these primitives interact strongly. Existing methods are evaluated by comparing predicted depth, normals, and segmentation against ground truth. The state of the art method involves a learned regression procedure to predict a start point consisting of a fixed number of primitives, followed by a descent method to refine the geometry and remove redundant primitives. CSG (Constructive Solid Geometry) representations are significantly enhanced by a set-differencing operation. Our representation incorporates negative primitives, which are differenced from the positive primitives. These notably enrich the geometry that the model can encode, while complicating the fitting problem. This paper presents a method that can (a) incorporate these negative primitives and (b) choose the overall number of positive and negative primitives by ensembling. Extensive experiments on the standard NYUv2 dataset confirm that (a) this approach results in substantial improvements in depth representation and segmentation over SOTA and (b) negative primitives improve fitting accuracy. Our method is robustly applicable across datasets: in a first, we evaluate primitive prediction for LAION images.