Abstract: Low-light image enhancement aims to recover clear, natural, and detail-preserving images from scenes with insufficient illumination, low contrast, noise degradation, and color distortion. Existing methods can improve image brightness to some extent, but they often suffer from noise amplification, unstable color restoration, texture loss, and over-enhancement in complex dark scenes. This is mainly because noise and textures may show similar high-frequency responses in the spatial domain, while luminance and chrominance information are highly coupled in the RGB space. To address these problems, this paper proposes SFSNet, a spatial-frequency synergistic network based on color space decomposition. The input image is first transformed into the HVI color space, where the intensity and chrominance components are separated to reduce the mutual interference between brightness recovery and color correction. Before spatial encoding, a frequency denoising module is introduced to suppress noise-related frequency disturbances and provide cleaner features for subsequent restoration. Then, a dual-branch backbone is constructed to process intensity and chrominance features separately, while a multi-scale convolution module is used to capture local textures, directional structures, and contextual information. To improve the consistency between brightness and color restoration, a cross-branch feature collaboration mechanism is designed to promote information interaction between the two branches. In addition, a deep interaction module and an uncertainty-based adaptive weighting strategy are employed to enhance deep feature representation and improve training stability. Experiments are conducted on LOL-v1, LOL-v2-real, and LOL-v2-syn, which provide paired normal-light reference images, and further evaluated on real unpaired datasets including DICM, LIME, MEF, and VV to verify the generalization ability of the proposed method. Compared with representative low-light enhancement methods, the proposed method can better improve dark-region brightness, suppress noise amplification, maintain natural color appearance, and preserve local structural details. Ablation studies further demonstrate the effectiveness of frequency denoising, multi-scale spatial modeling, cross-branch feature collaboration, and deep interaction supervision.

摘要： 低光照图像增强旨在从光照不足、对比度偏低、噪声显著和颜色失真的图像中恢复清晰、自然且细节完整的视觉内容，是夜间监控、移动摄影、自动驾驶和智能感知等场景中的重要基础任务。在现实中低光照图像的退化并非单一亮度衰减，而是由照度不足、暗区噪声、颜色偏移和结构细节弱化共同造成。现有方法虽然能够提升图像整体亮度，但在复杂暗光场景下仍容易出现噪声放大、色彩不稳定、局部纹理丢失和过增强等问题。其主要原因在于，噪声与纹理在空间域中往往具有相近的高频响应，若直接对空间进行处理，网络可能将噪声误作为有效细节进行增强；同时，RGB 空间中的亮度与色彩信息高度耦合，端到端增强过程容易使亮度恢复与颜色校正相互干扰，影响增强结果的真实性和一致性。针对上述问题，本文提出一种基于色彩空间解耦的空间-频率协同低光照图像增强网络 SFSNet。该方法首先利用 HVI 色彩空间将输入图像分解为亮度分量和色度分量，使网络能够分别建模亮度恢复和颜色表达，从而减弱二者之间的耦合影响。在此基础上，为降低低光噪声对后续空间恢复的干扰，本文在编码前引入频域去噪模块，通过频率域特征调制抑制噪声相关扰动，并保留对结构恢复有用的主要信息。随后，网络构建双分支协同主干，分别处理亮度特征和色度特征，并通过多尺度卷积模块增强对局部纹理、方向边缘和上下文信息的表达能力。为避免双分支独立恢复造成亮度与颜色不一致，本文进一步设计跨分支特征协同机制，在不同尺度上促进亮度分支与色度分支的信息交互，使亮度增强能够结合颜色结构约束，颜色恢复也能够感知照度变化。与此同时，本文在瓶颈层引入深度交互模块，通过深层特征融合生成辅助增强结果，并利用辅助监督强化网络对全局亮度分布和结构信息的建模能力。训练过程中，本文联合 sRGB 空间重建约束、HVI 空间一致性约束和瓶颈辅助监督，并采用不确定性自适应加权策略平衡不同目标的优化贡献，以提升模型训练的稳定性。本文在 LOL-v1、LOL-v2-real 和 LOL-v2-syn 数据集上进行定量评价，并在 DICM、LIME、MEF 和 VV 等真实无配对数据集上验证模型的泛化能力。结果表明，本文方法在 PSNR、SSIM、LPIPS、BRISQUE 和 NIQE 等评价指标上具有较强竞争力，并在视觉效果上能够较好地提升暗区亮度、抑制噪声放大、保持颜色自然性和恢复局部结构细节。与多种代表性低光照增强方法相比，SFSNet 在亮度恢复、色彩一致性和细节保持方面表现更加稳定。消融实验进一步证明，频域去噪、多尺度空间建模、跨分支特征协同和深度交互监督均对模型性能提升具有积极作用。综上，本文方法通过色彩解耦、频域净化、空间恢复和分支协同的联合设计，有效缓解了低光照图像增强中噪声退化、颜色失真与细节恢复相互耦合的问题，为复杂真实暗光场景下的图像增强提供了一种有效方案。