Improved Face Super-Resolution GenerativeAdversarial Networks
首发时间:2019-07-05
Abstract: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 propose 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, however, it is difficult to train. A simple and effective regularization method called spectral normalization GAN (SNGAN) 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.
keywords: Face super-resolution GAN spectral normalization dense blocks
点击查看论文中文信息
改进的人脸超分辨率生成对抗网络
摘要:人脸超分辨率方法用于从低分辨率图像生成高分辨率图像,以便更好地可视化。超分辨率生成对抗网络是一项具有开创性的工作,它可以生成具有逼真纹理的单个超分辨率图像。基于超分辨生成对抗网络,本文提出了改进的人脸超分辨率生成对抗网络。本文深入研究了超分辨生成对抗网络架构的关键组成部分,并对每个部分进行了改进,以实现更强大的超分辨生成对抗网络。首先,超分辨生成对抗网络使用残余块作为深度生成器网络的核心,本文决定采用密集卷积网络块(密集块)作为深度生成器网络。此外,尽管生成对抗网络性能优越,但难以训练。本文使用一种简单有效的正则化方法-谱归一化生成对抗网络来解决该问题。通过实验证实,本文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。
基金:
引用
No.****
同行评议
共计0人参与
勘误表
改进的人脸超分辨率生成对抗网络
评论
全部评论0/1000