Image/video denoising in low-light scenes is an extremely challenging problem due to limited photon count and high noise. In this paper, we propose a novel approach with contrastive learning to address this issue. Inspired by the success of contrastive learning used in some high-level computer vision tasks, we bring in this idea to the low-level denoising task. In order to achieve this goal, we introduce a new denoising contrastive regularization (DCR) to exploit the information of noisy images and clean images. In the feature space, DCR makes the denoised image closer to the clean image and far away from the noisy image. In addition, we build a new feature embedding network called Wnet, which is more effective to extract high-frequency information. We conduct the experiments on a real low-light dataset that captures still images taken on a moonless clear night in 0.6 millilux and videos under starlight (no moon present, <0.001 lux). The results show that our method can achieve a higher PSNR and better visual quality compared with existing methods

翻译：低光场景下的图像/视频去噪因光子计数受限和噪声水平极高而极具挑战性。本文提出一种基于对比学习的新方法来解决该问题。受对比学习在高层计算机视觉任务中成功应用的启发，我们将这一思想引入低层去噪任务。为此，我们提出一种新的去噪对比正则化（DCR）方法，用于挖掘含噪图像与干净图像的信息。在特征空间中，DCR使去噪图像更接近干净图像，同时远离含噪图像。此外，我们构建了一种新的特征嵌入网络Wnet，它更有效地提取高频信息。我们在一个真实低光数据集上进行了实验，该数据集包含无月晴朗夜晚0.6毫勒克斯下拍摄的静态图像，以及星光条件下（无月夜，<0.001勒克斯）的视频。结果表明，与现有方法相比，我们的方法能够获得更高的峰值信噪比（PSNR）和更优的视觉质量。