PolyGNN: Polyhedron-Based Graph Neural Network for 3D Building Reconstruction From Point Clouds

MCML Authors

Zhaiyu Chen

→ Group Xiaoxiang Zhu
 Data Science in Earth Observation

Zhitong Xiong

Dr.

→ Group Xiaoxiang Zhu
 Data Science in Earth Observation

Xiaoxiang Zhu

Prof. Dr.

Core PI

Data Science in Earth Observation

Abstract

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.

article CSN+24

---

ISPRS Journal of Photogrammetry and Remote Sensing

218.A. Dec. 2024.

---

Authors

Z. Chen • Y. Shi • L. Nan • Z. Xiong • X. Zhu

---

Links

DOI GitHub

---

Research Area

 C3 | Physics and Geo Sciences