Night images suffer not only from low light, but also from uneven distributions of light. Most existing night visibility enhancement methods focus mainly on enhancing low-light regions. This inevitably leads to over enhancement and saturation in bright regions, such as those regions affected by light effects (glare, floodlight, etc). To address this problem, we need to suppress the light effects in bright regions while, at the same time, boosting the intensity of dark regions. With this idea in mind, we introduce an unsupervised method that integrates a layer decomposition network and a light-effects suppression network. Given a single night image as input, our decomposition network learns to decompose shading, reflectance and light-effects layers, guided by unsupervised layer-specific prior losses. Our light-effects suppression network further suppresses the light effects and, at the same time, enhances the illumination in dark regions. This light-effects suppression network exploits the estimated light-effects layer as the guidance to focus on the light-effects regions. To recover the background details and reduce hallucination/artefacts, we propose structure and high-frequency consistency losses. Our quantitative and qualitative evaluations on real images show that our method outperforms state-of-the-art methods in suppressing night light effects and boosting the intensity of dark regions.
翻译:夜间图像不仅受到低光的影响,而且还受到光线分布不均的影响。大多数现有的夜间可见度增强方法主要侧重于加强低光区域,这不可避免地导致光区域,例如受光效应影响的区域(玻璃、洪光等)的增强和饱和程度过高。为了解决这一问题,我们需要抑制光光效应,同时提高黑暗区域的强度。考虑到这一想法,我们引入一种不受监督的方法,将层分解网络和光效抑制网络整合为一体。以单一的夜间图像作为投入,我们的分解网络学会在不受光效应影响的区域(如受光效应影响的区域(玻璃、洪光灯等)中解析阴影、反射和光效应层。为了解决这一问题,我们需要抑制光效应网络进一步抑制光效应,同时提高黑暗区域的亮度。这个光效应抑制网络利用了估计的光效应层作为光效应区域的指南。为了恢复黑暗细节,并减少在不受光效应特定层损失的情况下,在未受监督的层层层层中,我们提议在质量和高振动度方面采取我们的方法。