# Learning to Construct 3D Building Wireframes from 3D Line Clouds

arXiv: https://arxiv.org/abs/2208.11948 · HTML: https://mlsanity.com/paper/2208.11948/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 62 references that are in the map.
- First posted on arXiv 25 Aug 2022.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [ABC: A Big CAD Model Dataset For Geometric Deep Learning](https://mlsanity.com/paper/1812.06216/) (2018)
- [Line Segment Detection Using Transformers without Edges](https://mlsanity.com/paper/2101.01909/) (2021)
- [End-to-End Wireframe Parsing](https://mlsanity.com/paper/1905.03246/) (2019)
- [Learning to Parse Wireframes in Images of Man-Made Environments](https://mlsanity.com/paper/2007.07527/) (2020)
- [Holistically-Attracted Wireframe Parsing](https://mlsanity.com/paper/2003.01663/) (2020)
- [Learning Attraction Field Representation for Robust Line Segment Detection](https://mlsanity.com/paper/1812.02122/) (2018)
- [SOLD2: Self-supervised Occlusion-aware Line Description and Detection](https://mlsanity.com/paper/2104.03362/) (2021)
- [Deep Hough Transform for Semantic Line Detection](https://mlsanity.com/paper/2003.04676/) (2020)
- [Deep Hough-Transform Line Priors](https://mlsanity.com/paper/2007.09493/) (2020)
- [PPGNet: Learning Point-Pair Graph for Line Segment Detection](https://mlsanity.com/paper/1905.03415/) (2019)
- [Learning to Reconstruct 3D Manhattan Wireframes from a Single Image](https://mlsanity.com/paper/1905.07482/) (2019)
- [PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds](https://mlsanity.com/paper/2103.02766/) (2021)
- [TP-LSD: Tri-Points Based Line Segment Detector](https://mlsanity.com/paper/2009.05505/) (2020)
- [ELSD: Efficient Line Segment Detector and Descriptor](https://mlsanity.com/paper/2104.14205/) (2021)
- [Intuitive and Efficient Roof Modeling for Reconstruction and Synthesis](https://mlsanity.com/paper/2109.07683/) (2021)
- [A Minimal Closed-Form Solution for Multi-Perspective Pose Estimation using Points and Lines](https://mlsanity.com/paper/1807.09970/) (2018)
- [Surface Reconstruction from 3D Line Segments](https://mlsanity.com/paper/1911.00451/) (2019)
- [Hole-robust Wireframe Detection](https://mlsanity.com/paper/2111.15064/) (2021)
- [Simplifying Urban Data Fusion with BigSUR](https://mlsanity.com/paper/1807.00687/) (2018)

## Built on by (most cited first, 9 of 9)

- [3D Line Mapping Revisited](https://mlsanity.com/paper/2303.17504/) (2023)
- [Generating 3D House Wireframes with Semantics](https://mlsanity.com/paper/2407.12267/) (2024)
- [CLR-Wire: Towards Continuous Latent Representations for 3D Curve Wireframe Generation](https://mlsanity.com/paper/2504.19174/) (2025)
- [PBWR: Parametric Building Wireframe Reconstruction from Aerial LiDAR Point Clouds](https://mlsanity.com/paper/2311.12062/) (2023)
- [Explaining Human Preferences via Metrics for Structured 3D Reconstruction](https://mlsanity.com/paper/2503.08208/) (2025)
- [LineGS : 3D Line Segment Representation on 3D Gaussian Splatting](https://mlsanity.com/paper/2412.00477/) (2024)
- [BuildingWorld: A Structured 3D Building Dataset for Urban Foundation Models](https://mlsanity.com/paper/2511.06337/) (2025)
- [ZRG: A Dataset for Multimodal 3D Residential Rooftop Understanding](https://mlsanity.com/paper/2304.13219/) (2023)
- [SAVMap: Structure-Aided Visual Mapping of Large-Scale 2.5D Manhattan Wireframes from Panoramic Video](https://mlsanity.com/paper/2606.01939/) (2026)

## Abstract (arXiv)

Line clouds, though under-investigated in the previous work, potentially encode more compact structural information of buildings than point clouds extracted from multi-view images. In this work, we propose the first network to process line clouds for building wireframe abstraction. The network takes a line cloud as input , i.e., a nonstructural and unordered set of 3D line segments extracted from multi-view images, and outputs a 3D wireframe of the underlying building, which consists of a sparse set of 3D junctions connected by line segments. We observe that a line patch, i.e., a group of neighboring line segments, encodes sufficient contour information to predict the existence and even the 3D position of a potential junction, as well as the likelihood of connectivity between two query junctions. We therefore introduce a two-layer Line-Patch Transformer to extract junctions and connectivities from sampled line patches to form a 3D building wireframe model. We also introduce a synthetic dataset of multi-view images with ground-truth 3D wireframe. We extensively justify that our reconstructed 3D wireframe models significantly improve upon multiple baseline building reconstruction methods. The code and data can be found at https://github.com/Luo1Cheng/LC2WF.