FOTBCD: A Large-Scale Building Change Detection Benchmark from French Orthophotos and Topographic Data

TL;DR

FOTBCD is a comprehensive large-scale dataset for building change detection from French orthophotos, designed to improve cross-domain generalization and benchmark performance across diverse geographic environments.

Contribution

The paper introduces FOTBCD, a new large-scale, geographically diverse dataset for building change detection, including binary and instance-level annotations, to enhance benchmarking and generalization.

Findings

Geographic diversity improves cross-domain generalization.

FOTBCD outperforms existing datasets in benchmark tests.

Manual verification ensures high label quality.

Abstract

We introduce FOTBCD, a large-scale building change detection dataset derived from authoritative French orthophotos and topographic building data provided by IGN France. Unlike existing benchmarks that are geographically constrained to single cities or limited regions, FOTBCD spans 28 departments across mainland France, with 25 used for training and three geographically disjoint departments held out for evaluation. The dataset covers diverse urban, suburban, and rural environments at 0.2m/pixel resolution. We publicly release FOTBCD-Binary, a dataset comprising approximately 28,000 before/after image pairs with pixel-wise binary building change masks, each associated with patch-level spatial metadata. The dataset is designed for large-scale benchmarking and evaluation under geographic domain shift, with validation and test samples drawn from held-out departments and manually verified to ensure label quality. In addition, we publicly release FOTBCD-Instances, a publicly available instance-level annotated subset comprising several thousand image pairs, which illustrates the complete annotation schema used in the full instance-level version of FOTBCD. Using a fixed reference baseline, we benchmark FOTBCD-Binary against LEVIR-CD+ and WHU-CD, providing strong empirical evidence that geographic diversity at the dataset level is associated with improved cross-domain generalization in building change detection.