Learning Structural Graph Layouts and 3D Shapes for Long Span Bridges 3D Reconstruction

TL;DR

This paper introduces a learning-based 3D reconstruction approach for long-span bridges that leverages prior structural knowledge to accurately model complex topologies from images, overcoming challenges faced by traditional point cloud methods.

Contribution

The paper presents a novel topology-aware 3D reconstruction method that combines high-level structural graph layouts with low-level 3D shapes, tailored for complex bridge structures.

Findings

Successfully reconstructed 3D models of two real long-span steel truss bridges.

Demonstrated the method's ability to handle complex topologies and noise in point clouds.

Validated the approach's effectiveness in real-world scenarios.

Abstract

A learning-based 3D reconstruction method for long-span bridges is proposed in this paper. 3D reconstruction generates a 3D computer model of a real object or scene from images, it involves many stages and open problems. Existing point-based methods focus on generating 3D point clouds and their reconstructed polygonal mesh or fitting-based geometrical models in urban scenes civil structures reconstruction within Manhattan world constrains and have made great achievements. Difficulties arise when an attempt is made to transfer these systems to structures with complex topology and part relations like steel trusses and long-span bridges, this could be attributed to point clouds are often unevenly distributed with noise and suffer from occlusions and incompletion, recovering a satisfactory 3D model from these highly unstructured point clouds in a bottom-up pattern while preserving the geometrical and topological properties makes enormous challenge to existing algorithms. Considering the prior human knowledge that these structures are in conformity to regular spatial layouts in terms of components, a learning-based topology-aware 3D reconstruction method which can obtain high-level structural graph layouts and low-level 3D shapes from images is proposed in this paper. We demonstrate the feasibility of this method by testing on two real long-span steel truss cable-stayed bridges.