Building Extraction from Remote Sensing Imagery under Hazy and Low-light Conditions: Benchmark and Baseline

TL;DR

This paper introduces HaLoBuilding, a benchmark and a novel deep learning framework for extracting buildings from optical remote sensing images under hazy and low-light conditions, addressing a gap in real-world scenario performance.

Contribution

The paper presents the first benchmark specifically for adverse weather conditions and a new end-to-end model with modules designed to mitigate meteorological effects and improve building extraction accuracy.

Findings

HaLoBuild-Net outperforms state-of-the-art methods on the HaLoBuilding dataset.

The proposed modules effectively suppress weather-induced noise and sharpen boundaries.

The approach generalizes well across multiple remote sensing datasets.

Abstract

Building extraction from optical Remote Sensing (RS) imagery suffers from performance degradation under real-world hazy and low-light conditions. However, existing optical methods and benchmarks focus primarily on ideal clear-weather conditions. While SAR offers all-weather sensing, its side-looking geometry causes geometric distortions. To address these challenges, we introduce HaLoBuilding, the first optical benchmark specifically designed for building extraction under hazy and low-light conditions. By leveraging a same-scene multitemporal pairing strategy, we ensure pixel-level label alignment and high fidelity even under extreme degradation. Building upon this benchmark, we propose HaLoBuild-Net, a novel end-to-end framework for building extraction in adverse RS scenarios. At its core, we develop a Spatial-Frequency Focus Module (SFFM) to effectively mitigate meteorological interference on building features by coupling large receptive field attention with frequency-aware channel reweighting guided by stable low-frequency anchors. Additionally, a Global Multi-scale Guidance Module (GMGM) provides global semantic constraints to anchor building topologies, while a Mutual-Guided Fusion Module (MGFM) implements bidirectional semantic-spatial calibration to suppress shallow noise and sharpen weather-induced blurred boundaries. Extensive experiments demonstrate that HaLoBuild-Net significantly outperforms state-of-the-art methods and conventional cascaded restoration-segmentation paradigms on the HaLoBuilding dataset, while maintaining robust generalization on WHU, INRIA, and LoveDA datasets. The source code and datasets are publicly available at: https://github.com/AeroVILab-AHU/HaLoBuilding.