论文标题
通过级联的颜色和亮度补偿渲染夜间图像
Rendering Nighttime Image Via Cascaded Color and Brightness Compensation
论文作者
论文摘要
图像信号处理（ISP）对于相机成像至关重要，并且在白天场景中广泛部署了神经网络（NN）解决方案。缺乏足够的夜间图像数据集和有关夜间照明特征的见解，这对使用现有NN ISP的高质量渲染构成了巨大的挑战。为了解决这个问题，我们首先构建了一个高分辨率的夜间RAW-RGB（NR2R）数据集，并具有由专家专业人士注释的白平衡和音调映射。同时，为了最好地捕获夜间照明光源的特征，我们开发了CBUNET，这是一个两阶段的NN ISP，以级联色彩和亮度属性的补偿。实验表明，与传统的ISP管道相比，我们的方法具有更好的视觉质量，并且在NTIRE 2022 Night Photography构成挑战中排名第二，这是各自的人和专业摄影师选择的两种曲目。代码和相关材料可在我们的网站上：https：//njuvision.github.io/cbunet。
Image signal processing (ISP) is crucial for camera imaging, and neural networks (NN) solutions are extensively deployed for daytime scenes. The lack of sufficient nighttime image dataset and insights on nighttime illumination characteristics poses a great challenge for high-quality rendering using existing NN ISPs. To tackle it, we first built a high-resolution nighttime RAW-RGB (NR2R) dataset with white balance and tone mapping annotated by expert professionals. Meanwhile, to best capture the characteristics of nighttime illumination light sources, we develop the CBUnet, a two-stage NN ISP to cascade the compensation of color and brightness attributes. Experiments show that our method has better visual quality compared to traditional ISP pipeline, and is ranked at the second place in the NTIRE 2022 Night Photography Rendering Challenge for two tracks by respective People's and Professional Photographer's choices. The code and relevant materials are avaiable on our website: https://njuvision.github.io/CBUnet.
