Currently, Transformer is the most popular architecture for image dehazing, but due to its large computational complexity, its ability to handle long-range dependency is limited on resource-constrained devices. To tackle this challenge, we introduce the U-shaped Vision Mamba (UVM-Net), an efficient single-image dehazing network. Inspired by the State Space Sequence Models (SSMs), a new deep sequence model known for its power to handle long sequences, we design a Bi-SSM block that integrates the local feature extraction ability of the convolutional layer with the ability of the SSM to capture long-range dependencies. Extensive experimental results demonstrate the effectiveness of our method. Our method provides a more highly efficient idea of long-range dependency modeling for image dehazing as well as other image restoration tasks. The URL of the code is \url{https://github.com/zzr-idam/UVM-Net}. Our method takes only \textbf{0.009} seconds to infer a $325 \times 325$ resolution image (100FPS) without I/O handling time.

翻译：目前，Transformer是图像去雾领域最流行的架构，但由于其计算复杂度较高，在资源受限设备上处理长距离依赖的能力有限。为应对这一挑战，我们提出U型视觉曼巴（UVM-Net）——一种高效的单图像去雾网络。受状态空间序列模型（SSMs）启发，这种新型深度序列模型以其处理长序列的能力著称，我们设计了Bi-SSM模块，该模块融合了卷积层的局部特征提取能力与SSM捕获长距离依赖的能力。大量实验结果表明了我们方法的有效性。我们的方法为图像去雾及其他图像恢复任务提供了一种更高效的长距离依赖建模思路。代码URL为\url{https://github.com/zzr-idam/UVM-Net}。在不考虑输入/输出处理时间的情况下，我们推断一张$325 \times 325$分辨率的图像仅需\textbf{0.009}秒（100FPS）。