Decreased visibility, intensive noise, and biased color are the common problems existing in low-light images. These visual disturbances further reduce the performance of high-level vision tasks, such as object detection, and tracking. To address this issue, some image enhancement methods have been proposed to increase the image contrast. However, most of them are implemented only in the spatial domain, which can be severely influenced by noise signals while enhancing. Hence, in this work, we propose a novel residual recurrent multi-wavelet convolutional neural network R2-MWCNN learned in the frequency domain that can simultaneously increase the image contrast and reduce noise signals well. This end-to-end trainable network utilizes a multi-level discrete wavelet transform to divide input feature maps into distinct frequencies, resulting in a better denoise impact. A channel-wise loss function is proposed to correct the color distortion for more realistic results. Extensive experiments demonstrate that our proposed R2-MWCNN outperforms the state-of-the-art methods quantitively and qualitatively.

翻译：低可见度、强噪声及色彩偏差是低光图像中普遍存在的问题。这些视觉干扰进一步降低了高级视觉任务（如目标检测与跟踪）的性能。为解决该问题，已有多种图像增强方法被提出以提升图像对比度。然而，现有方法大多仅在空间域中实现，增强过程中易受噪声信号的严重影响。因此，本文提出一种在频域中学习的新型残差循环多波卷神经网络R2-MWCNN，能够同时有效提升图像对比度并抑制噪声信号。该端到端可训练网络利用多级离散小波变换将输入特征图划分为不同频带，从而实现更优的去噪效果。我们提出一种通道级损失函数以校正色彩失真，从而获得更真实的结果。大量实验表明，本文提出的R2-MWCNN在定量与定性指标上均优于现有最先进方法。