Abstract
Reconstructing degraded images is a critical task in image processing. Although CNN and Transformer-based models are prevalent in this field, they exhibit inherent limitations, such as inadequate long-range dependency modeling and high computational costs. To overcome these issues, we introduce the Channel-Aware U-Shaped Mamba (CU-Mamba) model, which incorporates a dual State Space Model (SSM) framework into the U-Net architecture. CU-Mamba employs a Spatial SSM module for global context encoding and a Channel SSM component to preserve channel correlation features, both in linear computational complexity relative to the feature map size. Extensive experimental results validate CU-Mamba's superiority over existing state-of-the-art methods, underscoring the importance of integrating both spatial and channel contexts in image restoration.
Abstract (translated)
重建失真图像是在图像处理领域一个关键的任务。尽管在图像处理领域中CNN和Transformer-based模型普遍存在，但它们存在固有局限性，例如不足以建模长距离依赖关系和计算成本高。为了克服这些限制，我们引入了通道感知U-shapedMamba（CU-Mamba）模型，该模型将双状态空间模型（SSM）框架融入到U-Net架构中。CU-Mamba采用空间SSM模块进行全局上下文编码，并使用通道SSM组件保留通道相关特征，在线性计算复杂度与特征图大小相对方面都具有优势。大量实验结果证实了CU-Mamba在现有最先进方法上的优越性，强调了在图像修复中整合空间和通道上下文的重要性。
URL
https://arxiv.org/abs/2404.11778
