Abstract
Recovering fine-grained details in extremely dark images remains challenging due to severe structural information loss and noise corruption. Existing enhancement methods often fail to preserve intricate details and sharp edges, limiting their effectiveness in downstream applications like text and edge detection. To address these deficiencies, we propose an efficient dual-stage approach centered on detail recovery for dark images. In the first stage, we introduce a Residual Fourier-Guided Module (RFGM) that effectively restores global illumination in the frequency domain. RFGM captures inter-stage and inter-channel dependencies through residual connections, providing robust priors for high-fidelity frequency processing while mitigating error accumulation risks from unreliable priors. The second stage employs complementary Mamba modules specifically designed for textural structure refinement: (1) Patch Mamba operates on channel-concatenated non-downsampled patches, meticulously modeling pixel-level correlations to enhance fine-grained details without resolution loss. (2) Grad Mamba explicitly focuses on high-gradient regions, alleviating state decay in state space models and prioritizing reconstruction of sharp edges and boundaries. Extensive experiments on multiple benchmark datasets and downstream applications demonstrate that our method significantly improves detail recovery performance while maintaining efficiency. Crucially, the proposed modules are lightweight and can be seamlessly integrated into existing Fourier-based frameworks with minimal computational overhead. Code is available at this https URL.
Abstract (translated)
在极暗图像中恢复细微细节仍然是一个挑战，因为这会导致严重的结构信息丢失和噪声干扰。现有的增强方法往往无法保留复杂的细节和锐利边缘，从而限制了它们在下游应用（如文本和边缘检测）中的有效性。为了弥补这些缺陷，我们提出了一种基于细节恢复的高效双阶段方法来处理暗图像。 第一阶段引入了一个残差傅里叶引导模块 (RFGM)，该模块能够有效恢复频率域内的全局照明。RFGM 通过残差连接捕捉跨阶段和跨通道依赖性，为高频处理提供稳健先验，并降低由于不可靠先验导致的误差累积风险。 第二阶段采用互补的 Mamba 模块，专门用于纹理结构细化：(1) Patch Mamba 在不进行下采样的通道级联补丁上操作，精细建模像素级别的相关性，增强细微细节而不损失分辨率。(2) Grad Mamba 明确关注高梯度区域，在状态空间模型中缓解了状态衰减问题，并优先重建锐利边缘和边界。 在多个基准数据集和下游应用上的广泛实验表明，我们的方法显著提高了细节恢复性能，同时保持了效率。至关重要的是，所提出的模块是轻量级的，可以无缝集成到现有的傅里叶基础框架中，并且几乎没有计算开销。 代码可在 [此处](https://此链接应由原作者提供，原文中的具体URL未给出) 获取。
URL
https://arxiv.org/abs/2508.03336
