Deep neural networks have achieved remarkable progress in enhancing low-light images by improving their brightness and eliminating noise. However, most existing methods construct end-to-end mapping networks heuristically, neglecting the intrinsic prior of image enhancement task and lacking transparency and interpretability. Although some unfolding solutions have been proposed to relieve these issues, they rely on proximal operator networks that deliver ambiguous and implicit priors. In this work, we propose a paradigm for low-light image enhancement that explores the potential of customized learnable priors to improve the transparency of the deep unfolding paradigm. Motivated by the powerful feature representation capability of Masked Autoencoder (MAE), we customize MAE-based illumination and noise priors and redevelop them from two perspectives: 1) \textbf{structure flow}: we train the MAE from a normal-light image to its illumination properties and then embed it into the proximal operator design of the unfolding architecture; and m2) \textbf{optimization flow}: we train MAE from a normal-light image to its gradient representation and then employ it as a regularization term to constrain noise in the model output. These designs improve the interpretability and representation capability of the model.Extensive experiments on multiple low-light image enhancement datasets demonstrate the superiority of our proposed paradigm over state-of-the-art methods. Code is available at https://github.com/zheng980629/CUE.

翻译：深度神经网络通过提升亮度与消除噪声，已在低光图像增强领域取得了显著进展。然而，现有方法大多启发式地构建端到端映射网络，忽视了图像增强任务的内在先验，缺乏透明性与可解释性。尽管已有展开式方法尝试缓解这些问题，但它们依赖能传递模糊隐式先验的近端算子网络。本文提出一种低光图像增强范式，探索定制化可学习先验的潜力以提升深度展开范式的透明性。受掩膜自编码器（MAE）强大特征表示能力的启发，我们定制了基于MAE的照度与噪声先验，并从两个角度对其进行重新开发：1）**结构流**：从正常光图像到其照度属性训练MAE，随后将其嵌入展开架构的近端算子设计中；2）**优化流**：从正常光图像到其梯度表示训练MAE，随后将其作为正则化项约束模型输出中的噪声。这些设计提升了模型的可解释性与表示能力。在多个低光图像增强数据集上的大量实验表明，本文提出的范式优于当前最先进方法。代码开源于https://github.com/zheng980629/CUE。