This paper presents a novel and interpretable end-to-end learning framework, called the deep compensation unfolding network (DCUNet), for restoring light field (LF) images captured under low-light conditions. DCUNet is designed with a multi-stage architecture that mimics the optimization process of solving an inverse imaging problem in a data-driven fashion. The framework uses the intermediate enhanced result to estimate the illumination map, which is then employed in the unfolding process to produce a new enhanced result. Additionally, DCUNet includes a content-associated deep compensation module at each optimization stage to suppress noise and illumination map estimation errors. To properly mine and leverage the unique characteristics of LF images, this paper proposes a pseudo-explicit feature interaction module that comprehensively exploits redundant information in LF images. The experimental results on both simulated and real datasets demonstrate the superiority of our DCUNet over state-of-the-art methods, both qualitatively and quantitatively. Moreover, DCUNet preserves the essential geometric structure of enhanced LF images much better. The code will be publicly available at https://github.com/lyuxianqiang/LFLL-DCU.

这篇论文介绍了一种新颖且可解释的端到端学习框架，称为深度补偿展开网络（DCUNet），用于恢复在低光条件下捕捉的光场（LF）图像。DCUNet设计了一个多阶段的架构，以数据驱动的方式模拟解决反向成像问题的优化过程。该框架使用中间增强的结果来估计光照图，然后在展开过程中使用该估计结果来产生新的增强结果。此外，DCUNet在每个优化阶段包括一个内容相关的深度补偿模块，用于抑制噪声和光照图估计误差。为了正确挖掘和利用LF图像的独特特征，本文提出了一个伪显式特征交互模块，全面利用LF图像中的冗余信息。对模拟和真实数据集的实验结果定性定量地证明了我们的DCUNet相对于现有方法的优越性。此外，DCUNet更好地保留了增强的LF图像的基本几何结构。代码将会公开在此URL。

使用深度补偿展开网络增强低光光场图像