...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Image Processing, IET >Deep residual refining based pseudo-multi-frame network for effective single image super-resolution
【24h】

Deep residual refining based pseudo-multi-frame network for effective single image super-resolution

机译：基于深度残差细化的伪多帧网络，可实现有效的单幅图像超分辨率

获取原文
获取原文并翻译 | 示例
   

获取外文期刊封面封底 >>

       
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Single image super-resolution (SISR) has gained great attraction and progress in recent years. Since the SISR is an ill-posed inverse problem, most researchers are concentrated on making efforts to learn effective and reasonable mapping functions from low-resolution observation to its potential high-resolution (HR) counterpart. In this study, the authors have proposed a deep residual refining based pseudo-multi-frame network for efficient SISR. A channel-wise attention mechanism is employed for residual refinement. It can ease residual learning process through explicitly modelling non-linear dependencies between channels by using global information embedding. Multiple potential HRs from different deconvolutional layers are further artificially learned, and then adaptively fused into final desired HR image. The authors call this strategy as pseudo-multi-frame SR. It could make full use of available redundant information possessed in hierarchical layers. They have evaluated the proposed network on several popular benchmark datasets. The experimental results have shown that the two highlights proposed can consistently boost final performance. The proposed network can outperform most of the state-of-the-art methods with acceptable less parameters.
机译：近年来，单图像超分辨率（SISR）获得了巨大的吸引力和进步。由于SISR是一个不适当地的逆问题，因此大多数研究人员都致力于研究从低分辨率观测到潜在的高分辨率（HR）的有效而合理的绘图功能。在这项研究中，作者提出了一种基于深度残差精炼的伪多帧网络，以实现有效的SISR。逐通道注意机制用于残差细化。通过使用全局信息嵌入对通道之间的非线性依存关系进行显式建模，可以简化残余学习过程。进一步人为地学习了来自不同反卷积层的多个潜在HR，然后将其自适应融合到最终所需的HR图像中。作者称这种策略为伪多帧SR。它可以充分利用层次结构层中拥有的可用冗余信息。他们在几个流行的基准数据集上评估了拟议的网络。实验结果表明，提出的两个亮点可以持续提高最终性能。所建议的网络可以用可接受的较少参数来胜过大多数现有技术。

著录项

  • 来源
    《Image Processing, IET》 |2019年第4期|591-599|共9页
  • 作者

    Mei Kangfu; Jiang Aiwen; Li Juncheng; Liu Bo; Ye Jihua; Wang Mingwen;

  • 作者单位

    Jiangxi Normal Univ, Sch Comp & Informat Engn, Nanchang, Jiangxi, Peoples R China;

    Jiangxi Normal Univ, Sch Comp & Informat Engn, Nanchang, Jiangxi, Peoples R China;

    East China Normal Univ, Sch Comp Sci & Software Engn, Shanghai, Peoples R China;

    Auburn Univ, Coll Comp Sci & Software Engn, Auburn, AL 36849 USA;

    Jiangxi Normal Univ, Sch Comp & Informat Engn, Nanchang, Jiangxi, Peoples R China;

    Jiangxi Normal Univ, Sch Comp & Informat Engn, Nanchang, Jiangxi, Peoples R China;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号