作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2008, Vol. 34 ›› Issue (5): 193-195. doi: 10.3969/j.issn.1000-3428.2008.05.068

• 人工智能及识别技术 • 上一篇    下一篇

基于学习的超分辨率技术

郑丽贤,何小海,吴 炜,杨晓敏,陈 默   

  1. (四川大学电子信息学院图像信息研究所,成都 610064)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2008-03-05 发布日期:2008-03-05

Learning-based Super-resolution Technique

ZHENG Li-xian, HE Xiao-hai, WU Wei, YANG Xiao-min, CHEN Mo   

  1. (Image Information Institute, College of Electronics and Information Engineering, Sichuan University, Chengdu 610064)
  • Received:1900-01-01 Revised:1900-01-01 Online:2008-03-05 Published:2008-03-05

摘要: 基于学习的超分辨率算法使用一个图像训练集来产生一个学习模型,运用该模型为输入的低分辨率图像创建更多的高频信息,获得比基于重建算法更好的结果。该文介绍了基于学习的超分辨率技术的相关工作、理论基础和主要算法,提出基于学习的超分辨率算法中仍需解决的关键问题,展望其在未来的研究发展方向。

关键词: 超分辨率, 马尔可夫随机场, 图像金字塔

Abstract: Learning-based super-resolution technique predicts the high-resolution images from the input low-resolution ones, through learning from a training set which consists of a large number of other high-resolution images. And the results are better than the reconstruction based super-resolution algorithms. The related work, theory and algorithms of learning-based super-resolution are illustrated. The crucial problems which need to be resolved in further work are proposed. Directions of future research are pointed.

Key words: super-resolution, Markov random field, image pyramid

中图分类号: