论文标题
Leugan：通过无监督的生成注意力网络增强的低光图像
LEUGAN:Low-Light Image Enhancement by Unsupervised Generative Attentional Networks
论文作者
论文摘要
从低光数据恢复图像是一个具有挑战性的问题。大多数现有的基于深网的算法旨在使用成对图像训练。由于缺乏现实世界数据集，在实际上在图像边缘和颜色信息的丢失方面概括时，它们通常的性能很差。在本文中，我们提出了一个无监督的生成网络，并具有注意力引导来处理低光图像增强任务。具体来说，我们的网络包含两个部分：一个边缘辅助模块，该模块可恢复更清晰的边缘和一个恢复更现实的颜色的注意力指南。此外，我们提出了一种新颖的损失功能，以使生成的图像的边缘更加可见。实验验证了我们提出的算法对最先进的方法的表现良好，尤其是对于现实世界图像，就图像清晰度和噪声控制而言。
Restoring images from low-light data is a challenging problem. Most existing deep-network based algorithms are designed to be trained with pairwise images. Due to the lack of real-world datasets, they usually perform poorly when generalized in practice in terms of loss of image edge and color information. In this paper, we propose an unsupervised generation network with attention-guidance to handle the low-light image enhancement task. Specifically, our network contains two parts: an edge auxiliary module that restores sharper edges and an attention guidance module that recovers more realistic colors. Moreover, we propose a novel loss function to make the edges of the generated images more visible. Experiments validate that our proposed algorithm performs favorably against state-of-the-art methods, especially for real-world images in terms of image clarity and noise control.
