Detail enhancement of image super-resolution based on detail synthesis

详细信息    查看全文

• 作者：Jinsheng Xiao^a ; ^b ; ^{xiaojs@whu.edu.cn}Author Vitae ; Enyu Liu^aAuthor Vitae ; Ling Zhao^aAuthor Vitae ; Yuan-Fang Wang^bAuthor Vitae ; Wenbin Jiang^cAuthor Vitae
• 关键词：Super resolution ; Detail enhancement ; Singular value decomposition ; Local self-similarity
• 刊名：Signal Processing: Image Communication
• 出版年：2017
• 出版时间：February 2017
• 年：2017
• 卷：50
• 期：Complete
• 页码：21-33
• 全文大小：3016 K
• 卷排序：50

文摘

A detail-enhancement and super-resolution algorithm based on detail synthesis is proposed. It combines local self-similarity search and singular value decomposition of patches together. The high-frequency block is reconstructed using effective singular values. It improved the facet or line phenomenon on edges and areas that have rich texture. The method is also applicable to other super-resolution algorithm in detail enhancement.