Premium
Generative Adversarial Image Super‐Resolution Through Deep Dense Skip Connections
Author(s) -
Zhu Xiaobin,
Li Zhuangzi,
Zhang Xiaoyu,
Li Haisheng,
Xue Ziyu,
Wang Lei
Publication year - 2018
Publication title -
computer graphics forum
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.578
H-Index - 120
eISSN - 1467-8659
pISSN - 0167-7055
DOI - 10.1111/cgf.13568
Subject(s) - discriminator , computer science , artificial intelligence , image (mathematics) , convolutional neural network , feature (linguistics) , adversarial system , pattern recognition (psychology) , ground truth , pipeline (software) , generator (circuit theory) , representation (politics) , generative grammar , deep learning , generative adversarial network , function (biology) , telecommunications , linguistics , philosophy , power (physics) , physics , quantum mechanics , evolutionary biology , detector , politics , political science , law , biology , programming language
Recently, image super‐resolution works based on Convolutional Neural Networks (CNNs) and Generative Adversarial Nets (GANs) have shown promising performance. However, these methods tend to generate blurry and over‐smoothed super‐resolved (SR) images, due to the incomplete loss function and powerless architectures of networks. In this paper, a novel generative adversarial image super‐resolution through deep dense skip connections (GSR‐DDNet), is proposed to solve the above‐mentioned problems. It aims to take advantage of GAN's ability of modeling data distributions, so that GSR‐DDNet can select informative feature representation and model the mapping across the low‐quality and high‐quality images in an adversarial way. The pipeline of the proposed method consists of three main components: 1) The generator of a novel dense skip connection network with the deep structure for learning robust mapping function is proposed to generate SR images from low‐resolution images; 2) The feature extraction network based on VGG‐19 is adopted to capture high frequency feature maps for content loss; and 3) The discriminator with Wasserstein distance is adopted to identify the overall style of SR and ground‐truth images. Experiments conducted on four publicly available datasets demonstrate the superiority against the state‐of‐the‐art methods.