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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Zhaiyu, Shi, Yilei, Nan, Liangliang, Xiong, Zhitong, Zhu, Xiao Xiang
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914970219839488
author Chen, Zhaiyu
Shi, Yilei
Nan, Liangliang
Xiong, Zhitong
Zhu, Xiao Xiang
author_facet Chen, Zhaiyu
Shi, Yilei
Nan, Liangliang
Xiong, Zhitong
Zhu, Xiao Xiang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2307_08636
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle PolyGNN: Polyhedron-based Graph Neural Network for 3D Building Reconstruction from Point Clouds
Chen, Zhaiyu
Shi, Yilei
Nan, Liangliang
Xiong, Zhitong
Zhu, Xiao Xiang
Computer Vision and Pattern Recognition
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.
title PolyGNN: Polyhedron-based Graph Neural Network for 3D Building Reconstruction from Point Clouds
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2307.08636