• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >Coarse-to-Fine Learning for Single-Image Super-Resolution
【24h】

Coarse-to-Fine Learning for Single-Image Super-Resolution

机译：从粗到精细的学习以获得单图像超分辨率

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This paper develops a coarse-to-fine framework for single-image super-resolution (SR) reconstruction. The coarse-to-fine approach achieves high-quality SR recovery based on the complementary properties of both example learning-and reconstruction-based algorithms: example learning-based SR approaches are useful for generating plausible details from external exemplars but poor at suppressing aliasing artifacts, while reconstruction-based SR methods are propitious for preserving sharp edges yet fail to generate fine details. In the coarse stage of the method, we use a set of simple yet effective mapping functions, learned via correlative neighbor regression of grouped low-resolution (LR) to high-resolution (HR) dictionary atoms, to synthesize an initial SR estimate with particularly low computational cost. In the fine stage, we devise an effective regularization term that seamlessly integrates the properties of local structural regularity, nonlocal self-similarity, and collaborative representation over relevant atoms in a learned HR dictionary, to further improve the visual quality of the initial SR estimation obtained in the coarse stage. The experimental results indicate that our method outperforms other state-learned HR dictionaryof-the-art methods for producing high-quality images despite that both the initial SR estimation and the followed enhancement are cheap to implement.
机译：本文为单图像超分辨率（SR）重建开发了一个从粗到精的框架。粗到精方法基于示例学习算法和基于重建算法的互补特性，可实现高质量的SR恢复：基于示例学习的SR方法可用于从外部示例生成合理的细节，但在抑制混叠伪像方面效果较差，虽然基于重建的SR方法有利于保留锐利边缘，但无法生成精细的细节。在该方法的粗略阶段，我们使用一组简单而有效的映射函数，通过将低分辨率（LR）分组为高分辨率（HR）字典原子的相关邻域回归来学习，以合成初始SR估计值，特别是计算成本低。在精细阶段，我们设计了一个有效的正则化术语，该术语将学习的HR词典中的局部原子结构规则性，非局部自相似性和相关原子的协作表示无缝整合，以进一步提高获得的初始SR估计的视觉质量在粗糙的阶段。实验结果表明，尽管初始SR估计和随后的增强都难以实现，但我们的方法优于其他国家学习的HR字典来生成高质量图像。

著录项

  • 来源
  • 作者

    Kaibing Zhang; Dacheng Tao; Xinbo Gao; Xuelong Li; Jie Li;

  • 作者单位

    School of Computer and Information Science, Hubei Engineering University, Xiaogan, P. R. China;

    Centre for Quantum Computation & Intelligent Systems and the Faculty of Engineering and Information Technology, University of Technology Sydney, 81 Broadway Street, Ultimo, NSW, Australia;

    State Key Laboratory of Integrated Services Networks, School of Electronic Engineering, Xidian University, Xi’an, P. R. China;

    Center for OPTical IMagery Analysis and Learning (OPTIMAL), State Key Laboratory of Transient Optics and Photonics, Xi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi’an, P. R. China;

    Video and Image Processing System Laboratory, School of Electronic Engineering, Xidian University, Xi’an, P. R. China;

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

    Dictionaries; Image reconstruction; Image edge detection; Estimation; Electronic mail; Image resolution; Learning systems;

    机译：词典;图像重建;图像边缘检测;估计;电子邮件;图像分辨率;学习系统;

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