Multi-scale non-local kernel regression for super resolution

Haichao Zhang, Jianchao Yang, Yanning Zhang, Thomas S. Huang

科研成果: 书/报告/会议事项章节会议稿件同行评审

6 引用 (Scopus)

摘要

In this paper, we propose an extension of the Non-Local Kernel Regression (NL-KR) method and apply it to super-resolution (SR) tasks. The proposed method extends NL-KR via generalizing the self-similarity from single-scale to multi-scale, and propose an effective SR algorithm using the proposed multi-scale NL-KR model. Experimental results on both synthetic and real images demonstrate the effectiveness of the proposed method.

源语言英语
主期刊名ICIP 2011
主期刊副标题2011 18th IEEE International Conference on Image Processing
1353-1356
页数4
DOI
出版状态已出版 - 2011
活动2011 18th IEEE International Conference on Image Processing, ICIP 2011 - Brussels, 比利时
期限: 11 9月 201114 9月 2011

出版系列

姓名Proceedings - International Conference on Image Processing, ICIP
ISSN(印刷版)1522-4880

会议

会议2011 18th IEEE International Conference on Image Processing, ICIP 2011
国家/地区比利时
Brussels
时期11/09/1114/09/11

指纹

探究 'Multi-scale non-local kernel regression for super resolution' 的科研主题。它们共同构成独一无二的指纹。

引用此