Abstract
Recent learning-based underwater image enhancement (UIE) methods have advanced by incorporating physical priors into deep neural networks, particularly using the signal-to-noise ratio (SNR) prior to reduce wavelength-dependent attenuation. However, spatial domain SNR priors have two limitations: (i) they cannot effectively separate cross-channel interference, and (ii) they provide limited help in amplifying informative structures while suppressing noise. To overcome these, we propose using the SNR prior in the frequency domain, decomposing features into amplitude and phase spectra for better channel modulation. We introduce the Fourier Attention SNR-prior Transformer (FAST), combining spectral interactions with SNR cues to highlight key spectral components. Additionally, the Frequency Adaptive Transformer (FAT) bottleneck merges low- and high-frequency branches using a gated attention mechanism to enhance perceptual quality. Embedded in a unified U-shaped architecture, these modules integrate a conventional RGB stream with an SNR-guided branch, forming SFormer. Trained on 4,800 paired images from UIEB, EUVP, and LSUI, SFormer surpasses recent methods with a 3.1 dB gain in PSNR and 0.08 in SSIM, successfully restoring colors, textures, and contrast in underwater scenes.
Abstract (translated)
最近基于学习的水下图像增强（UIE）方法通过在深度神经网络中引入物理先验而取得了进展，特别是利用信噪比（SNR）先验来减少波长依赖性衰减。然而，在空间域中的SNR先验存在两个局限：(i) 它们无法有效分离跨通道干扰；(ii) 它们在放大信息结构的同时抑制噪声方面提供的帮助有限。为克服这些问题，我们提出在频域中使用SNR先验，并将特征分解为振幅和相位谱，以实现更好的通道调制。我们引入了傅立叶注意信噪比先验变换器（FAST），结合光谱交互与SNR线索，突出关键的频谱成分。此外，频率自适应变换器（FAT）瓶颈通过门控注意力机制将低频和高频分支合并起来以提升感知质量。这些模块嵌入统一的U形架构中，整合了传统的RGB流与由SNR引导的分支，形成了SFormer。在UIEB、EUVP和LSUI数据集中的4,800对图像上进行训练后，SFormer超越了近期方法，在PSNR方面提高了3.1 dB，并且SSIM提升了0.08，成功恢复了水下场景的颜色、纹理和对比度。
URL
https://arxiv.org/abs/2508.18664
