Structured Outdoor Architecture Reconstruction by Exploration and Classification
This work addresses the challenge of enhancing architectural reconstruction accuracy for applications in urban planning or mapping, though it is incremental as it builds upon existing reconstruction methods.
The paper tackles the problem of improving imperfect building reconstructions from aerial images by proposing an explore-and-classify framework that iteratively modifies models and classifies their correctness, resulting in consistent quality improvements across various initial reconstruction algorithms.
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.