U-Shaped Dual Attention Vision Mamba Network for Satellite Remote Sensing Single-Image Dehazing

In remote sensing single-image dehazing (RSSID), adjacency effects and the multi-scale characteristics of the land surface–atmosphere system highlight the importance of a network’s effective receptive field (ERF) and its ability to capture multi-scale features. Although multi-scale hybrid models combining convolutional neural networks and Transformers show promise, the quadratic complexity of Transformer complicates the balance between ERF and efficiency. Recently, Mamba achieved global ERF with linear complexity and excelled in modeling long-range dependencies, yet its design for sequential data and channel redundancy limits its direct applicability to RSSID. To overcome these challenges and improve performance in RSSID, we present a novel Mamba-based dehazing network, U-shaped Dual Attention Vision Mamba Network (UDAVM-Net) for Satellite RSSID, which integrates multi-path scanning and incorporates dual attention mechanisms to better capture non-uniform haze features while reducing redundancy. The core module, Residual Vision Mamba Blocks (RVMBs), are stacked within a U-Net architecture to enhance multi-scale feature learning. Furthermore, to enhance the model’s applicability to real-world remote sensing data, we abandoned overly simplified haze image degradation models commonly used in existing works, instead adopting an atmospheric radiative transfer model combined with a cloud distortion model to construct a submeter-resolution satellite RSSID dataset. Experimental results demonstrate that UDAVM-Net consistently outperforms competing methods on the StateHaze1K dataset, our newly proposed dataset, and real-world remote sensing images, underscoring its effectiveness in diverse scenarios.