Context-aware single image super-resolution using locality-constrained group sparse representation

Chih Yun Tsai*, De An Huang, Min Chun Yang, Li Wei Kang, Yu Chiang Frank Wang

*此作品的通信作者

研究成果: 書貢獻/報告類型會議論文篇章

12 引文 斯高帕斯(Scopus)

摘要

We present a novel learning-based method for single image super-resolution (SR). Given a single input low-resolution (LR) image (and its image pyramid), we propose to learn context-specific image sparse representation, which aims at modeling the relationship between low and high-resolution image patch pairs of different context categories in terms of the learned dictionaries. To predict the SR image, we derive the context-specific sparse representation of each image patch in the LR input with additional locality and group sparsity constraints. While the locality constraint searches for the most similar image patches and uses the corresponding highresolution outputs for SR, the group sparsity constraint allows us to utilize the information from most relevant context categories for predicting the final SR output. Experimental results show the proposed method is able to quantitatively and qualitatively achieve state-of-the-art performance.

原文英語
主出版物標題2012 IEEE Visual Communications and Image Processing, VCIP 2012
DOIs
出版狀態已發佈 - 2012
對外發佈
事件2012 IEEE Visual Communications and Image Processing, VCIP 2012 - San Diego, CA, 美国
持續時間: 2012 11月 272012 11月 30

出版系列

名字2012 IEEE Visual Communications and Image Processing, VCIP 2012

會議

會議2012 IEEE Visual Communications and Image Processing, VCIP 2012
國家/地區美国
城市San Diego, CA
期間2012/11/272012/11/30

ASJC Scopus subject areas

  • 電腦視覺和模式識別

指紋

深入研究「Context-aware single image super-resolution using locality-constrained group sparse representation」主題。共同形成了獨特的指紋。

引用此