ES-DETR: Edge-Guided State-Space DETR for Foggy Remote Sensing Object Detection

Abstract

Object detection in optical remote sensing imagery is severely affected by adverse weather conditions, such as fog and haze, which degrade image quality and obscure structural details. Although recent Transformer-based detectors have achieved promising performance, they suffer from quadratic computational complexity for high-resolution inputs and tend to produce imprecise object boundaries in degraded scenes. To address these issues, we propose an Edge-Guided State-Space DETR (ES-DETR), an end-to-end detection framework that integrates linear-complexity state-space modeling with structural priors. Specifically, a Laplacian Edge-Aware Module (LEM) is designed to extract high-frequency boundary information from foggy images. Moreover, a Structural-Prior-Driven Mamba Fusion Module (SMF) is introduced to incorporate edge-derived structural priors into the Mamba architecture for long-range dependency modeling and feature fusion. This design effectively restores degraded semantic representations. Extensive experiments on foggy remote sensing benchmarks demonstrate that the proposed ES-DETR outperforms state-of-the-art detectors while maintaining a favorable accuracy–efficiency trade-off.