<p>Underwater image enhancement plays a crucial role in safeguarding national security in underwater domains. As the preprocessing step to address challenges such as blurriness and color distortion encountered during underwater imaging, Underwater image enhancement greatly aids in detecting underwater threat targets. However, due to the oversight of utilizing frequency domain information, the existing underwater image enhancement techniques often fail to achieve satisfactory results, leading to subpar reconstruction of degraded images. To tackle these problems, we propose a fusing Frequency and Spatial Domain Transformer network called FSformer for underwater image enhancement. We first devise a novel Frequency-Space Global–Local Transformer block (FSGLT), which not just adaptively integrates information from the frequency and spatial domains, but also enables the model to focus more on severely degraded areas in underwater images. Additionally, a Dual-Branch Feature Enhancement Module (DBFEM) is designed for enhancing extracted deep-level features separately on both the spatial and frequency branches, thereby boosting the ability to restore more details and improve overall image quality in underwater scenarios. On the UIEB dataset, our proposed method achieved PSNR and SSIM values of 24.112 and 0.907 respectively. Through extensive ablation studies and comparative analyses on both synthetic and real-world datasets, we show the effectiveness and superiority of our proposed approach.</p>