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

Yicheng Luo (Beijing University of Posts and Telecommunications),* Jing Ren (ETH Zurich), Xuefei Zhe (Tencent AI lab), Di Kang (Tencent), Yajing Xu (Beijing University of Posts and Telecommunications), Peter Wonka (KAUST), Linchao Bao (Tencent AI Lab)
The 33rd British Machine Vision Conference


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.



author    = {Yicheng Luo and Jing Ren and Xuefei Zhe and Di Kang and Yajing Xu and Peter Wonka and Linchao Bao},
title     = {Learning to Construct 3D Building Wireframes from 3D Line Clouds},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year      = {2022},
url       = {https://bmvc2022.mpi-inf.mpg.de/0091.pdf}

Copyright © 2022 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection