# PolyGNN: Polyhedron-based Graph Neural Network for 3D Building Reconstruction from Point Clouds

arXiv: https://arxiv.org/abs/2307.08636 · HTML: https://mlsanity.com/paper/2307.08636/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 73 references that are in the map.
- First posted on arXiv 17 Jul 2023.

## Builds on (most cited first, 21 of 21)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [BSP-Net: Generating Compact Meshes via Binary Space Partitioning](https://mlsanity.com/paper/1911.06971/) (2019)
- [CvxNet: Learnable Convex Decomposition](https://mlsanity.com/paper/1909.05736/) (2019)
- [Points2Surf: Learning Implicit Surfaces from Point Cloud Patches](https://mlsanity.com/paper/2007.10453/) (2020)
- [Topology Adaptive Graph Convolutional Networks](https://mlsanity.com/paper/1710.10370/) (2017)
- [Supervised Fitting of Geometric Primitives to 3D Point Clouds](https://mlsanity.com/paper/1811.08988/) (2018)
- [Neural Fields as Learnable Kernels for 3D Reconstruction](https://mlsanity.com/paper/2111.13674/) (2021)
- [CPFN: Cascaded Primitive Fitting Networks for High-Resolution Point Clouds](https://mlsanity.com/paper/2109.00113/) (2021)
- [City3D: Large-Scale Building Reconstruction from Airborne LiDAR Point Clouds](https://mlsanity.com/paper/2201.10276/) (2022)
- [Reconstructing Compact Building Models from Point Clouds Using Deep Implicit Fields](https://mlsanity.com/paper/2112.13142/) (2021)
- [Neural Vector Fields: Implicit Representation by Explicit Learning](https://mlsanity.com/paper/2303.04341/) (2023)
- [Automated 3D reconstruction of LoD2 and LoD1 models for all 10 million buildings of the Netherlands](https://mlsanity.com/paper/2201.01191/) (2021)
- [Virtual laser scanning with HELIOS++: A novel take on ray tracing-based simulation of topographic 3D laser scanning](https://mlsanity.com/paper/2101.09154/) (2021)
- [A Survey and Benchmark of Automatic Surface Reconstruction from Point Clouds](https://mlsanity.com/paper/2301.13656/) (2023)
- [3D Shapes Local Geometry Codes Learning with SDF](https://mlsanity.com/paper/2108.08593/) (2021)
- [Large-scale Building Height Retrieval from Single SAR Imagery based on Bounding Box Regression Networks](https://mlsanity.com/paper/2111.09460/) (2021)
- [Neural Vector Fields for Implicit Surface Representation and Inference](https://mlsanity.com/paper/2204.06552/) (2022)
- [ImpliCity: City Modeling from Satellite Images with Deep Implicit Occupancy Fields](https://mlsanity.com/paper/2201.09968/) (2022)

## Built on by (most cited first, 10 of 10)

- [Parametric Point Cloud Completion for Polygonal Surface Reconstruction](https://mlsanity.com/paper/2503.08363/) (2025)
- [TUM2TWIN: Introducing the Large-Scale Multimodal Urban Digital Twin Benchmark Dataset](https://mlsanity.com/paper/2505.07396/) (2025)
- [Beyond Grid Data: Exploring Graph Neural Networks for Earth Observation](https://mlsanity.com/paper/2411.03223/) (2024)
- [Reconstructing Building Height from Spaceborne TomoSAR Point Clouds Using a Dual-Topology Network](https://mlsanity.com/paper/2601.00658/) (2026)
- [BuildAnyPoint: 3D Building Structured Abstraction from Diverse Point Clouds](https://mlsanity.com/paper/2602.23645/) (2026)
- [Point2Building: Reconstructing Buildings from Airborne LiDAR Point Clouds](https://mlsanity.com/paper/2403.02136/) (2024)
- [WindMiL: Equivariant Graph Learning for Wind Loading Prediction](https://mlsanity.com/paper/2511.01226/) (2025)
- [OCCDiff: Occupancy Diffusion Model for High-Fidelity 3D Building Reconstruction from Noisy Point Clouds](https://mlsanity.com/paper/2512.08506/) (2025)
- [Unified Primitive Proxies for Structured Shape Completion](https://mlsanity.com/paper/2601.00759/) (2026)
- [KODAMA: Multimodal Digital Twin Reconstruction for Urban RF Propagation Modelling](https://mlsanity.com/paper/2609.07298/) (2026)

## Abstract (arXiv)

We present PolyGNN, a polyhedron-based graph neural network for 3D building reconstruction from point clouds. PolyGNN learns to assemble primitives obtained by polyhedral decomposition via graph node classification, achieving a watertight and compact reconstruction. To effectively represent arbitrary-shaped polyhedra in the neural network, we propose a skeleton-based sampling strategy to generate polyhedron-wise queries. These queries are then incorporated with inter-polyhedron adjacency to enhance the classification. PolyGNN is end-to-end optimizable and is designed to accommodate variable-size input points, polyhedra, and queries with an index-driven batching technique. To address the abstraction gap between existing city-building models and the underlying instances, and provide a fair evaluation of the proposed method, we develop our method on a large-scale synthetic dataset with well-defined ground truths of polyhedral labels. We further conduct a transferability analysis across cities and on real-world point clouds. Both qualitative and quantitative results demonstrate the effectiveness of our method, particularly its efficiency for large-scale reconstructions. The source code and data are available at https://github.com/chenzhaiyu/polygnn.