CAMSR: Content-Aware State Space Model for Lightweight Image Super-Resolution

Mamba has demonstrated significant potential in image super-resolution (SR) due to its linear computational complexity and excellent long-range modeling capabilities. Existing studies typically employ multidirectional scanning to overcome Mamba’s inherent causal constraints, enhancing spatial relationship modeling. However, multidirectional scanning significantly increases computational overhead, undermining Mamba’s advantage in terms of computational complexity. In this work, we conduct a systematic analysis of multidirectional scanning schemes through LAM visualization results and quantitative metric evaluation. Then, we propose CAMSR, a non-causal lightweight SR model based on Mamba that achieves similar content perception. Specifically, it uses a content-aware sequence generator (CASG) to cluster content-similar feature tokens and generate a reordered sequence of similar feature clusters. Subsequently, a content-aware state-space equation facilitates long-range pixel interactions and captures global context through prompt learning. Finally, spatial and channel-level attention mechanisms further refine features, achieving an effective balance between reconstruction quality and computational complexity. The experimental results demonstrate that our approach achieves superior performance compared with state-of-the-art methods while using fewer parameters. The code is available athttps://github.com/nathan66666/CAMSR.git.