SAMamba: Stream Alignment Mamba for Motion Infrared Small Target Detection

The key to infrared small target detection lies in distinguishing targets from backgrounds for accurate extraction. However, long-distance imaging with low angular resolution causes morphology loss and weak saliency, making targets easily submerged in complex backgrounds. As a result, achieving high-probability, low-false-alarm detection solely in the spatial domain is challenging. To address this, we extend to the spatiotemporal domain and propose Stream Alignment Mamba for Motion Infrared Small Target Detection (SAMamba). Specifically, we first design a Stream Mamba Block based on a dynamic state space model, which introduces bidirectional spatiotemporal scanning to explore inter-frame relationships in sequential images, not only preserving spatial correlations but also leveraging the causality of temporal cues for comprehensive global background representation. Second, we develop a Cross-Frame Feature Enhancement Block to implicitly align feature streams by computing local responses between neighboring and reference frames, thereby strengthening weak target features. In addition, we devise a Hierarchical Feature Alignment Block with adaptive adjustment strategies and position-aware mechanisms to address spatial misalignment during upsampling, thus enhancing the effectiveness of multi-scale target fusion and ultimately improving detection accuracy. Extensive experiments on IRDST, IRSatVideo-LEO, and TSIRMT datasets demonstrate that our method achieves significant advantages over state-of-the-art (SOTA) approaches.