Learning an Enhancement Convolutional Neural Network for Multi-degraded Images
Learning an Enhancement Convolutional Neural Network for Multi-degraded Images
复制标题
学习多退化图像的增强卷积神经网络
DOI：
10.1007/s11220-020-00289-0
复制
发表时间：
2020-05-23
影响因子：
2.2
通讯作者：
Zhang, Jing
中科院分区：
文献类型：
--
作者：
Wang, Ke;Zhuo, Li;Zhang, Jing
虽然图像增强方法已经广泛应用于各种户外视觉系统中，但现有的方法仍然面临两个关键问题。一方面，现有的方法只考虑单一的退化。然而，在实际应用中，图像质量通常会受到多种因素的影响。针对单一退化因子设计的方法在处理多重退化图像时不能取得很好的效果。另一方面，基于图像模型的增强方法，利用先验知识或手工特征进行图像增强，可能会带来一些拟合误差。因此，考虑到图像的多重退化，本文提出了一种图像增强方法。首先，提出了一种新的基于多重散射模型的图像退化模型，用于表征雾霾、模糊和噪声混合引起的多重退化。然后，提出了一种基于ResNet的图像增强卷积神经网络（CNN），直接在像素域学习低质量图像和高质量图像之间的隐式映射模型。CNN网络已经用端到端的学习方式进行了训练。在合成数据集和真实图像上的实验结果验证了该方法的优越性，并与现有方法进行了比较。
Although image enhancement methods have been widely applied in various outdoor vision systems, the existing methods still face two critical problems. On the one hand, the existing methods only consider a single degradation. However, in practical applications, image quality is usually degraded by multiple factors. The methods designed for the single degradation factor cannot achieve good performance when facing multi-degraded images. On the other hand, the imaging model-based enhancement methods which use prior knowledge or handcrafted features to perform image enhancement may bring some fitting errors. Therefore, considering multiple degradations in images, an image enhancement method is proposed in this paper. Firstly, a new image degradation model based on the multiple scattering model is proposed, which is used to characterize multiple degradations caused by haze, mixed with blur and noise. Then, an image enhancement convolutional neural network (CNN) based on ResNet is proposed to learn the implicit mapping model between low-quality and high-quality images in the pixel domain directly. The CNN network has been trained with an end-to-end learning manner. Experimental results on the synthetic dataset and real-world hazy images verify the superiority of the proposed method, while compared with the state-of-the-art methods.