Generative Adversarial Image Super-Resolution Through Deep Dense Skip Connections
| dc.contributor.author | Zhu, Xiaobin | en_US |
| dc.contributor.author | Li, Zhuangzi | en_US |
| dc.contributor.author | Zhang, Xiaoyu | en_US |
| dc.contributor.author | Li, Haisheng | en_US |
| dc.contributor.author | Xue, Ziyu | en_US |
| dc.contributor.author | Wang, Lei | en_US |
| dc.contributor.editor | Fu, Hongbo and Ghosh, Abhijeet and Kopf, Johannes | en_US |
| dc.date.accessioned | 2018-10-07T14:59:46Z | |
| dc.date.available | 2018-10-07T14:59:46Z | |
| dc.date.issued | 2018 | |
| dc.description.abstract | 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. | en_US |
| dc.description.number | 7 | |
| dc.description.sectionheaders | Towards Better Quality of Images/Videos | |
| dc.description.seriesinformation | Computer Graphics Forum | |
| dc.description.volume | 37 | |
| dc.identifier.doi | 10.1111/cgf.13568 | |
| dc.identifier.issn | 1467-8659 | |
| dc.identifier.pages | 289-300 | |
| dc.identifier.uri | https://doi.org/10.1111/cgf.13568 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.1111/cgf13568 | |
| dc.publisher | The Eurographics Association and John Wiley & Sons Ltd. | en_US |
| dc.subject | Computing methodologies | |
| dc.subject | Image processing | |
| dc.subject | Computer systems organization | |
| dc.subject | Neural networks | |
| dc.title | Generative Adversarial Image Super-Resolution Through Deep Dense Skip Connections | en_US |