Cross-domain heterogeneous residual network for single image super-resolution | |
Ji, Li5; Zhu, Qinghui5; Zhang, Yongqin4,5; Yin, Juanjuan5; Wei, Ruyi3; Xiao, Jinsheng3; Xiao, Deqiang2; Zhao, Guoying1 | |
刊名 | Neural Networks |
2022-05 | |
卷号 | 149页码:84-94 |
关键词 | Neural networks Neural network architecture Image restoration Image resolution |
ISSN号 | 08936080;18792782 |
DOI | 10.1016/j.neunet.2022.02.008 |
产权排序 | 2 |
英文摘要 | Single image super-resolution is an ill-posed problem, whose purpose is to acquire a high-resolution image from its degraded observation. Existing deep learning-based methods are compromised on their performance and speed due to the heavy design (i.e., huge model size) of networks. In this paper, we propose a novel high-performance cross-domain heterogeneous residual network for super-resolved image reconstruction. Our network models heterogeneous residuals between different feature layers by hierarchical residual learning. In outer residual learning, dual-domain enhancement modules extract the frequency-domain information to reinforce the space-domain features of network mapping. In middle residual learning, wide-activated residual-in-residual dense blocks are constructed by concatenating the outputs from previous blocks as the inputs into all subsequent blocks for better parameter efficacy. In inner residual learning, wide-activated residual attention blocks are introduced to capture direction- and location-aware feature maps. The proposed method was evaluated on four benchmark datasets, indicating that it can construct the high-quality super-resolved images and achieve the state-of-the-art performance. Code and pre-trained models are available at https://github.com/zhangyongqin/HRN. © 2022 Elsevier Ltd |
语种 | 英语 |
出版者 | Elsevier Ltd |
内容类型 | 期刊论文 |
源URL | [http://ir.opt.ac.cn/handle/181661/95781] |
专题 | 西安光学精密机械研究所_光学影像学习与分析中心 |
通讯作者 | Zhang, Yongqin |
作者单位 | 1.Center for Machine Vision and Signal Analysis, University of Oulu, Oulu; 90014, Finland 2.School of Optics and Photonics, Beijing Institute of Technology, Beijing; 100081, China; 3.Electronic Information School, Wuhan University, Wuhan; 430072, China; 4.CAS Key Laboratory of Spectral Imaging Technology, Xi'an; 710119, China; 5.School of Information Science and Technology, Northwest University, Xi'an; 710127, China; |
推荐引用方式 GB/T 7714 | Ji, Li,Zhu, Qinghui,Zhang, Yongqin,et al. Cross-domain heterogeneous residual network for single image super-resolution[J]. Neural Networks,2022,149:84-94. |
APA | Ji, Li.,Zhu, Qinghui.,Zhang, Yongqin.,Yin, Juanjuan.,Wei, Ruyi.,...&Zhao, Guoying.(2022).Cross-domain heterogeneous residual network for single image super-resolution.Neural Networks,149,84-94. |
MLA | Ji, Li,et al."Cross-domain heterogeneous residual network for single image super-resolution".Neural Networks 149(2022):84-94. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论