# Reconstructing Compact Building Models from Point Clouds Using Deep Implicit Fields

arXiv: https://arxiv.org/abs/2112.13142 · HTML: https://mlsanity.com/paper/2112.13142/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 53 references that are in the map.
- First posted on arXiv 24 Dec 2021.

## Builds on (most cited first, 5 of 5)

- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [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)

## Built on by (most cited first, 20 of 20)

- [PolyGNN: Polyhedron-based Graph Neural Network for 3D Building Reconstruction from Point Clouds](https://mlsanity.com/paper/2307.08636/) (2023)
- [ImpliCity: City Modeling from Satellite Images with Deep Implicit Occupancy Fields](https://mlsanity.com/paper/2201.09968/) (2022)
- [HTC-DC Net: Monocular Height Estimation from Single Remote Sensing Images](https://mlsanity.com/paper/2309.16486/) (2023)
- [Parametric Point Cloud Completion for Polygonal Surface Reconstruction](https://mlsanity.com/paper/2503.08363/) (2025)
- [Concise Plane Arrangements for Low-Poly Surface and Volume Modelling](https://mlsanity.com/paper/2404.06154/) (2024)
- [A Survey of Methods for Converting Unstructured Data to CSG Models](https://mlsanity.com/paper/2305.01220/) (2023)
- [Prompt-Driven Building Footprint Extraction in Aerial Images with Offset-Building Model](https://mlsanity.com/paper/2310.16717/) (2023)
- [Beyond Grid Data: Exploring Graph Neural Networks for Earth Observation](https://mlsanity.com/paper/2411.03223/) (2024)
- [APC2Mesh: Bridging the gap from occluded building faccades to full 3D models](https://mlsanity.com/paper/2404.02391/) (2024)
- [TSE-Net: Semi-supervised Monocular Height Estimation from Single Remote Sensing Images](https://mlsanity.com/paper/2511.13552/) (2025)
- [BuildAnyPoint: 3D Building Structured Abstraction from Diverse Point Clouds](https://mlsanity.com/paper/2602.23645/) (2026)
- [StructuredMesh: 3D Structured Optimization of Faccade Components on Photogrammetric Mesh Models using Binary Integer Programming](https://mlsanity.com/paper/2306.04184/) (2023)
- [Structure-preserving Planar Simplification for Indoor Environments](https://mlsanity.com/paper/2408.06814/) (2024)
- [GeoTexBuild: 3D Building Model Generation from Map Footprints](https://mlsanity.com/paper/2504.08419/) (2025)
- [Unified Primitive Proxies for Structured Shape Completion](https://mlsanity.com/paper/2601.00759/) (2026)
- [Confidence-Driven Facade Refinement of 3D Building Models Using MLS Point Clouds](https://mlsanity.com/paper/2604.03797/) (2026)
- [Hierarchical Space Partition for Surface Reconstruction](https://mlsanity.com/paper/2606.04891/) (2026)
- [TopoGS: Planar Reconstruction via Topology-aware 3D Gaussian Splatting](https://mlsanity.com/paper/2607.16838/) (2026)
- [KODAMA: Multimodal Digital Twin Reconstruction for Urban RF Propagation Modelling](https://mlsanity.com/paper/2609.07298/) (2026)
- [AstraLOD3: Zero-shot multimodal agentic reconstruction of LOD3 building models](https://mlsanity.com/paper/2609.28061/) (2026)

## Abstract (arXiv)

While three-dimensional (3D) building models play an increasingly pivotal role in many real-world applications, obtaining a compact representation of buildings remains an open problem. In this paper, we present a novel framework for reconstructing compact, watertight, polygonal building models from point clouds. Our framework comprises three components: (a) a cell complex is generated via adaptive space partitioning that provides a polyhedral embedding as the candidate set; (b) an implicit field is learned by a deep neural network that facilitates building occupancy estimation; (c) a Markov random field is formulated to extract the outer surface of a building via combinatorial optimization. We evaluate and compare our method with state-of-the-art methods in generic reconstruction, model-based reconstruction, geometry simplification, and primitive assembly. Experiments on both synthetic and real-world point clouds have demonstrated that, with our neural-guided strategy, high-quality building models can be obtained with significant advantages in fidelity, compactness, and computational efficiency. Our method also shows robustness to noise and insufficient measurements, and it can directly generalize from synthetic scans to real-world measurements. The source code of this work is freely available at https://github.com/chenzhaiyu/points2poly.