Abstract: For multiple scale factors of face super-resolution, a face super-resolution method based on very deep convolutional neural network was proposed; and through experiments, it was found that the increase of network depth can effectively improve the accuracy of face reconstruction. Firstly, a network that consists of 20 convolution layers were designed to learn an end-to-end mapping between the low-resolution images and the high-resolution images, and many small filters were cascaded to extract more textural information. Secondly, a residual-learning method was introduced to solve the problem of detail information loss caused by increasing depth. In addition, the low-resolution face images with multiple scale factors were merged to one training set to enable the network to achieve the face super resolution with multiple scale factors. The results on the CASPEAL test dataset show that the proposed method based on this very deep convolutional neural network has 2.7 dB increasement in Peak Signal-to-Noise Ratio (PSNR), and 2% increasement in structural similarity compared to the Bicubic based face reconstruction method. Compared with the SRCNN method, there is also a greater improvement. as well as a greater improvement in accuracy and visual improvement. It means that deeper network structures can achieve better results in reconstruction.

Key words: super-resolution reconstruction, convolutional neural network, machine learning, deep learning, residual learning

摘要： 针对多种放大倍数的人脸超分辨率重建问题，提出一种基于极深卷积神经网络的人脸超分辨率重建方法，并通过实验发现增加网络深度能够有效提升人脸重建的精度。首先，设计一个包含20个卷积层的网络从低分辨率图片和高分辨率图片之间学习一种端到端的映射关系，并通过在网络结构中将多个小的滤波器进行多次串联以扩大提取纹理信息的范围。其次，引入了残差学习的方法来解决随着深度的提升细节信息丢失的问题。另外，将不同放大因子的低分辨率人脸图片融合到一个训练集中训练，使得该卷积网络能够解决不同放大因子的人脸超分辨率重建问题。在CASPEAL测试集上的结果显示，该极深卷积神经网络的方法比基于双三次插值的人脸重建方法在峰值信噪比（PSNR）和结构相似度上有2.7 dB和2%的提升，和SRCNN的方法比较也有较大的提升，在精度和视觉改善方面都有较大提升。这显示了更深的网络结构能够在重建中取得更好的结果。

关键词: 超分辨率重建, 卷积神经网络, 机器学习, 深度学习, 残差学习