The face super-resolution method is used for generating high-resolution images from low-resolution ones for better visualization. The super-resolution generative adversarial network (SRGAN) can generate a single super-resolution image with realistic textures, which is a groundbreaking work. Based on SRGAN, we proposed improved face super-resolution generative adversarial networks. The super-resolution image details generated by SRGAN usually have undesirable artifacts. To further improve visual quality, we delve into the key components of the SRGAN network architecture and improve each part to achieve a more powerful SRGAN. First, the SRGAN employs residual blocks as the core of the very deep generator network G. In this paper, we decide to employ dense convolutional network blocks (dense blocks), which connect each layer to every other layer in a feed-forward fashion as our very deep generator networks. Moreover, in the past few years, generative adversarial networks (GANs) have been applied to solve various problems. Despite its superior performance, it is difficult to train. A simple and effective regularization method called spectral normalization GAN is used to solve this problem. We have experimentally confirmed that our proposed method is superior to the other existing method in training stability and visual improvements.

中文翻译：

---

改进的人脸超分辨率生成对抗网络

面部超分辨率方法用于从低分辨率图像生成高分辨率图像，以实现更好的可视化效果。超分辨率生成对抗网络（SRGAN）可以生成具有逼真的纹理的单个超分辨率图像，这是一项开创性的工作。基于SRGAN，我们提出了改进的人脸超分辨率生成对抗网络。SRGAN生成的超分辨率图像细节通常具有不希望的伪影。为了进一步提高视觉质量，我们深入研究了SRGAN网络体系结构的关键组件，并对每个部分进行了改进以实现更强大的SRGAN。首先，SRGAN采用残差块作为超深度生成器网络G的核心。在本文中，我们决定采用密集的卷积网络块（密集块），它以前馈的方式将每一层与其他每一层连接起来，作为我们非常深入的发电机网络。此外，在过去几年中，生成对抗网络（GAN）已被用于解决各种问题。尽管性能出色，但训练起来却很困难。一种简单有效的正则化方法（称为频谱归一化GAN）用于解决此问题。我们已经通过实验证实，我们提出的方法在训练稳定性和视觉改善方面优于其他现有方法。一种简单有效的正则化方法（称为频谱归一化GAN）用于解决此问题。我们已经通过实验证实，我们提出的方法在训练稳定性和视觉改善方面优于其他现有方法。一种简单有效的正则化方法（称为频谱归一化GAN）用于解决此问题。我们已经通过实验证实，我们提出的方法在训练稳定性和视觉改善方面优于其他现有方法。