Lightweight vision Mamba for weather-degraded remote sensing image restoration

In the field of remote sensing, the acquired images are often severely degraded due to adverse weather conditions, such as haze and raindrops, posing significant challenges for subsequent visual tasks. Although CNN and Transformer have been widely applied to address these issues, they struggle to balance the relationship between global scene recovery, local detail preservation, and computational efficiency, leading to an imbalance between model performance and efficiency. To this end, we propose a lightweight and efficient visual state space model for remote sensing image restoration. Specifically, we propose the Efficient Vision Mamba Block as the core component of the model, incorporating the State Space Model to leverage its linear complexity for modeling long-range dependencies. Furthermore, we design a multi-router scanning strategy to perform global modeling of remote sensing images, capturing large spatial features from different routes and directions. Compared with existing methods that employ fixed-direction scanning, our approach avoids information redundancy caused by repeated scanning, making the model better adaptable to the complex and changeable weather conditions. Extensive experiments validate the superiority of our proposed model, outperforming state-of-the-art methods on both the StateHaze1k and UAV-Rain1k datasets.