Computer vision applied to super resolution

被引：164

作者：

Capel, D ^{[1
]}

Zisserman, A ^{[1
]}

机构：

[1] Univ Oxford, Visual Geometry Grp, Oxford OX1 2JD, England

来源：

IEEE SIGNAL PROCESSING MAGAZINE | 2003年 / 20卷 / 03期

关键词：

D O I：

10.1109/MSP.2003.1203211

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

The application of super-resolution (SR) restoration technique in the field of computer vision is discussed. Given a set of observed images, the technique estimate an image at a higher resolution than is present in any of the individual images. The two key component of (SR) restoration technique is the accurate alignment of the LR images and the formulation of an SR estimator that uses a generative image model together with a prior model of the super-resolved image itself.

引用

页码：75 / 86

页数：12

共 36 条

[1]

[Anonymous], THESIS U OXFORD

[2]

[Anonymous], P ECCV

[3] Limits on super-resolution and how to break them [J].

Baker, S ;

Kanade, T .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (09) :1167-1183

[4]

Bascle B., 1996, P ECCV, P312

[5]

Bishop C. M., 1995, NEURAL NETWORKS PATT

[6] Automated mosaicing with super-resolution zoom [J].

Capel, D ;

Zisserman, A .

1998 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1998, :885-891

[7]

CAPEL DP, 2001, P IEEE C COMP VIS PA

[8]

CAPEL DP, 2003, IMAGE MOSAICING SUPE

[9]

DEVERNAY F, 1995, SPIE, V2567

[10]

Engl H., 1996, Mathematics and Its Applications, V375, DOI DOI 10.1007/978-94-009-1740-8

← 1 2 3 4 →