论文标题
基于Itinex的GAN管道利用配对和未配对的数据集来增强弱光图像
A Retinex based GAN Pipeline to Utilize Paired and Unpaired Datasets for Enhancing Low Light Images
论文作者
论文摘要
低光图像增强是发展强大的计算机视觉算法的重要挑战。基于配对数据集的机器学习方法是无监督，监督的，或者是根据未配对数据集进行监督的。本文提出了一条新颖的深度学习管道，可以从配对和未配对的数据集中学习。优化以最大程度地减少标准损失的卷积神经网络（CNN），并且已优化以最小化对抗性损失的生成对抗网络（GAN）用于实现低光图像增强过程的不同步骤。循环一致性损失和修补的歧视者被利用来进一步提高性能。本文还分析了不同组件，隐藏层和整个管道的功能和性能。
Low light image enhancement is an important challenge for the development of robust computer vision algorithms. The machine learning approaches to this have been either unsupervised, supervised based on paired dataset or supervised based on unpaired dataset. This paper presents a novel deep learning pipeline that can learn from both paired and unpaired datasets. Convolution Neural Networks (CNNs) that are optimized to minimize standard loss, and Generative Adversarial Networks (GANs) that are optimized to minimize the adversarial loss are used to achieve different steps of the low light image enhancement process. Cycle consistency loss and a patched discriminator are utilized to further improve the performance. The paper also analyses the functionality and the performance of different components, hidden layers, and the entire pipeline.
