Point cloud segmentation using hierarchical tree for architectural models

TL;DR

This paper introduces a hierarchical tree-based segmentation method for 3D point clouds of architectural models, leveraging a neural network to classify segments with high accuracy, addressing challenges in existing primitive-based segmentation techniques.

Contribution

The paper presents a novel hierarchical tree algorithm combined with HollowNets for primitive-based point cloud segmentation, improving accuracy over existing methods.

Findings

Achieved over 90% accuracy on domes and minarets

Effective segmentation of architectural features

Validated on real and synthetic data

Abstract

Recent developments in the 3D scanning technologies have made the generation of highly accurate 3D point clouds relatively easy but the segmentation of these point clouds remains a challenging area. A number of techniques have set precedent of either planar or primitive based segmentation in literature. In this work, we present a novel and an effective primitive based point cloud segmentation algorithm. The primary focus, i.e. the main technical contribution of our method is a hierarchical tree which iteratively divides the point cloud into segments. This tree uses an exclusive energy function and a 3D convolutional neural network, HollowNets to classify the segments. We test the efficacy of our proposed approach using both real and synthetic data obtaining an accuracy greater than 90% for domes and minarets.