Structured Outdoor Architecture Reconstruction by Exploration and Classification

TL;DR

This paper introduces an explore-and-classify framework for improving structured outdoor architectural reconstructions from aerial images by iteratively exploring model variations and classifying their correctness.

Contribution

The novel framework combines exploration and classification to enhance reconstruction accuracy, outperforming baseline and state-of-the-art methods.

Findings

Consistently improves reconstruction quality

Effective exploration of model space

Robust classification of building models

Abstract

This paper presents an explore-and-classify framework for structured architectural reconstruction from an aerial image. Starting from a potentially imperfect building reconstruction by an existing algorithm, our approach 1) explores the space of building models by modifying the reconstruction via heuristic actions; 2) learns to classify the correctness of building models while generating classification labels based on the ground-truth, and 3) repeat. At test time, we iterate exploration and classification, seeking for a result with the best classification score. We evaluate the approach using initial reconstructions by two baselines and two state-of-the-art reconstruction algorithms. Qualitative and quantitative evaluations demonstrate that our approach consistently improves the reconstruction quality from every initial reconstruction.