For the task of low-light image enhancement, deep learning-based algorithms have demonstrated superiority and effectiveness compared to traditional methods. Existing deep learning algorithms are proposed mainly based on the Retinex theory but overlook the noise and color distortion present in the input, which frequently results in significant noise amplification and local color distortion in the final results. To address this, we propose a Dual-Path Error Compensation method (DPEC), which aims to improve image quality in low-light conditions. DPEC performs precise pixel-level error estimation, which accurately captures subtle pixels differences, and independent denoising, which effectively removes unnecessary noise. This method restores image brightness while preserving local texture details and avoiding noise amplification. Furthermore, to compensate for the traditional CNN's limited ability to capture long-range semantic information and considering both computational speed and resource efficiency, we integrated the VMamba architecture into the backbone of DPEC. In addition, we introduced the HIS-Retinex loss to constrain the training of DPEC, ensuring that the overall brightness distribution of the images more closely aligns with real-world conditions. Comprehensive quantitative and qualitative experimental results demonstrate that our algorithm significantly outperforms state-of-the-art methods across six benchmark tests.

翻译：针对低光图像增强任务，基于深度学习的算法相较于传统方法已展现出优越性与有效性。现有深度学习算法主要基于Retinex理论构建，但往往忽略了输入图像中存在的噪声与色彩失真问题，这常导致最终结果出现显著的噪声放大与局部色彩失真。为解决此问题，我们提出一种双路径误差补偿方法（DPEC），旨在提升低光条件下的图像质量。DPEC通过精确的像素级误差估计（可准确捕捉细微像素差异）与独立去噪（能有效消除冗余噪声）相结合，在恢复图像亮度的同时保持局部纹理细节并避免噪声放大。此外，为弥补传统CNN在捕获长程语义信息方面的局限性，并兼顾计算速度与资源效率，我们将VMamba架构集成至DPEC的主干网络中。同时，我们引入HIS-Retinex损失函数以约束DPEC的训练过程，确保图像的整体亮度分布更贴合真实场景。全面的定量与定性实验结果表明，我们的算法在六项基准测试中均显著优于现有先进方法。