Designing a composite dictionary adaptively from joint examples

Zhangyang Wang; Yingzhen Yang; Jianchao Yang; Thomas Huang

doi:10.1109/VCIP.2015.7457839

Designing a composite dictionary adaptively from joint examples

Zhangyang Wang, Yingzhen Yang, Jianchao Yang, Thomas Huang

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Scopus citations

Abstract

We study the complementary behaviors of external and internal examples in image restoration, and are motivated to formulate a composite dictionary design framework. The composite dictionary consists of the global part learned from external examples, and the sample-specific part learned from internal examples. The dictionary atoms in both parts are further adaptively weighted to emphasize their model statistics. Experiments demonstrate that the joint utilization of external and internal examples leads to substantial improvements, with successful applications in image denoising and super resolution.

Original language	English (US)
Title of host publication	2015 Visual Communications and Image Processing, VCIP 2015
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781467373142
DOIs	https://doi.org/10.1109/VCIP.2015.7457839
State	Published - Apr 21 2016
Externally published	Yes
Event	Visual Communications and Image Processing, VCIP 2015 - Singapore, Singapore Duration: Dec 13 2015 → Dec 16 2015

Publication series

Name	2015 Visual Communications and Image Processing, VCIP 2015

Conference

Conference	Visual Communications and Image Processing, VCIP 2015
Country/Territory	Singapore
City	Singapore
Period	12/13/15 → 12/16/15

ASJC Scopus subject areas

Computer Networks and Communications
Signal Processing

Access to Document

10.1109/VCIP.2015.7457839

Cite this

Designing a composite dictionary adaptively from joint examples. / Wang, Zhangyang; Yang, Yingzhen; Yang, Jianchao et al.

2015 Visual Communications and Image Processing, VCIP 2015. Institute of Electrical and Electronics Engineers Inc., 2016. 7457839 (2015 Visual Communications and Image Processing, VCIP 2015).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Wang, Z, Yang, Y, Yang, J & Huang, T 2016, Designing a composite dictionary adaptively from joint examples. in 2015 Visual Communications and Image Processing, VCIP 2015., 7457839, 2015 Visual Communications and Image Processing, VCIP 2015, Institute of Electrical and Electronics Engineers Inc., Visual Communications and Image Processing, VCIP 2015, Singapore, Singapore, 12/13/15. https://doi.org/10.1109/VCIP.2015.7457839

@inproceedings{a304114e3e594ae5934a9bbe38344552,

title = "Designing a composite dictionary adaptively from joint examples",

abstract = "We study the complementary behaviors of external and internal examples in image restoration, and are motivated to formulate a composite dictionary design framework. The composite dictionary consists of the global part learned from external examples, and the sample-specific part learned from internal examples. The dictionary atoms in both parts are further adaptively weighted to emphasize their model statistics. Experiments demonstrate that the joint utilization of external and internal examples leads to substantial improvements, with successful applications in image denoising and super resolution.",

author = "Zhangyang Wang and Yingzhen Yang and Jianchao Yang and Thomas Huang",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE. Copyright: Copyright 2017 Elsevier B.V., All rights reserved.; Visual Communications and Image Processing, VCIP 2015 ; Conference date: 13-12-2015 Through 16-12-2015",

year = "2016",

month = apr,

day = "21",

doi = "10.1109/VCIP.2015.7457839",

language = "English (US)",

series = "2015 Visual Communications and Image Processing, VCIP 2015",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2015 Visual Communications and Image Processing, VCIP 2015",

}

TY - GEN

T1 - Designing a composite dictionary adaptively from joint examples

AU - Wang, Zhangyang

AU - Yang, Yingzhen

AU - Yang, Jianchao

AU - Huang, Thomas

PY - 2016/4/21

Y1 - 2016/4/21

N2 - We study the complementary behaviors of external and internal examples in image restoration, and are motivated to formulate a composite dictionary design framework. The composite dictionary consists of the global part learned from external examples, and the sample-specific part learned from internal examples. The dictionary atoms in both parts are further adaptively weighted to emphasize their model statistics. Experiments demonstrate that the joint utilization of external and internal examples leads to substantial improvements, with successful applications in image denoising and super resolution.

AB - We study the complementary behaviors of external and internal examples in image restoration, and are motivated to formulate a composite dictionary design framework. The composite dictionary consists of the global part learned from external examples, and the sample-specific part learned from internal examples. The dictionary atoms in both parts are further adaptively weighted to emphasize their model statistics. Experiments demonstrate that the joint utilization of external and internal examples leads to substantial improvements, with successful applications in image denoising and super resolution.

UR - http://www.scopus.com/inward/record.url?scp=84978959053&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84978959053&partnerID=8YFLogxK

U2 - 10.1109/VCIP.2015.7457839

DO - 10.1109/VCIP.2015.7457839

M3 - Conference contribution

AN - SCOPUS:84978959053

T3 - 2015 Visual Communications and Image Processing, VCIP 2015

BT - 2015 Visual Communications and Image Processing, VCIP 2015

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - Visual Communications and Image Processing, VCIP 2015

Y2 - 13 December 2015 through 16 December 2015

ER -

Designing a composite dictionary adaptively from joint examples

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this