Adaptive Lattice-Aware Image Demosaicking Using Global and Local Information

Ji Soo Kim; Keunsoo Ko; Chang Su Kim

doi:10.1109/ICIP40778.2020.9190936

Adaptive Lattice-Aware Image Demosaicking Using Global and Local Information

Ji Soo Kim, Keunsoo Ko, Chang Su Kim

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

3 Citations (Scopus)

Abstract

A novel approach for image demosaicking based on adaptive lattice-aware filter (ALF) and global refinement unit (GRU) is proposed in this work. We generate ALFs dynamically, which are adaptive to positions of pixels within color lattices in a color filter array, to obtain a locally demosaicked image. We then refine the locally demosaicked image using GRU to exploit global information, as well as local information. To extend the receptive fields efficiently, we adopt dilated convolutions in GRU. Experimental results demonstrate that the proposed algorithm provides the state-of-the-art performances in standard demosaicking datasets.

Original language	English
Title of host publication	2020 IEEE International Conference on Image Processing, ICIP 2020 - Proceedings
Publisher	IEEE Computer Society
Pages	483-487
Number of pages	5
ISBN (Electronic)	9781728163956
DOIs	https://doi.org/10.1109/ICIP40778.2020.9190936
Publication status	Published - 2020 Oct
Event	2020 IEEE International Conference on Image Processing, ICIP 2020 - Virtual, Abu Dhabi, United Arab Emirates Duration: 2020 Sept 25 → 2020 Sept 28

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2020-October
ISSN (Print)	1522-4880

Conference

Conference	2020 IEEE International Conference on Image Processing, ICIP 2020
Country/Territory	United Arab Emirates
City	Virtual, Abu Dhabi
Period	20/9/25 → 20/9/28

Bibliographical note

Funding Information:
This work was supported in part by the MSIT, Korea, under the ITRC support program (IITP-2020-2016-0-00464) supervised by the IITP and in part by the National Research Foundation of Korea (NRF) through the Korea Government (MSIP) under Grant NRF-2018R1A2B3003896.

Publisher Copyright:
© 2020 IEEE.

Keywords

Bayer pattern
Demosaicking
adaptive filters
convolutional neural networks

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.1109/ICIP40778.2020.9190936

Cite this

Kim, J. S., Ko, K., & Kim, C. S. (2020). Adaptive Lattice-Aware Image Demosaicking Using Global and Local Information. In 2020 IEEE International Conference on Image Processing, ICIP 2020 - Proceedings (pp. 483-487). Article 9190936 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2020-October). IEEE Computer Society. https://doi.org/10.1109/ICIP40778.2020.9190936

Adaptive Lattice-Aware Image Demosaicking Using Global and Local Information. / Kim, Ji Soo; Ko, Keunsoo; Kim, Chang Su.
2020 IEEE International Conference on Image Processing, ICIP 2020 - Proceedings. IEEE Computer Society, 2020. p. 483-487 9190936 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2020-October).

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

Kim, JS, Ko, K & Kim, CS 2020, Adaptive Lattice-Aware Image Demosaicking Using Global and Local Information. in 2020 IEEE International Conference on Image Processing, ICIP 2020 - Proceedings., 9190936, Proceedings - International Conference on Image Processing, ICIP, vol. 2020-October, IEEE Computer Society, pp. 483-487, 2020 IEEE International Conference on Image Processing, ICIP 2020, Virtual, Abu Dhabi, United Arab Emirates, 20/9/25. https://doi.org/10.1109/ICIP40778.2020.9190936

@inproceedings{4a8fae90d0e249c19531dd5dda313432,

title = "Adaptive Lattice-Aware Image Demosaicking Using Global and Local Information",

abstract = "A novel approach for image demosaicking based on adaptive lattice-aware filter (ALF) and global refinement unit (GRU) is proposed in this work. We generate ALFs dynamically, which are adaptive to positions of pixels within color lattices in a color filter array, to obtain a locally demosaicked image. We then refine the locally demosaicked image using GRU to exploit global information, as well as local information. To extend the receptive fields efficiently, we adopt dilated convolutions in GRU. Experimental results demonstrate that the proposed algorithm provides the state-of-the-art performances in standard demosaicking datasets.",

keywords = "Bayer pattern, Demosaicking, adaptive filters, convolutional neural networks",

author = "Kim, {Ji Soo} and Keunsoo Ko and Kim, {Chang Su}",

note = "Funding Information: This work was supported in part by the MSIT, Korea, under the ITRC support program (IITP-2020-2016-0-00464) supervised by the IITP and in part by the National Research Foundation of Korea (NRF) through the Korea Government (MSIP) under Grant NRF-2018R1A2B3003896. Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE International Conference on Image Processing, ICIP 2020 ; Conference date: 25-09-2020 Through 28-09-2020",

year = "2020",

month = oct,

doi = "10.1109/ICIP40778.2020.9190936",

language = "English",

series = "Proceedings - International Conference on Image Processing, ICIP",

publisher = "IEEE Computer Society",

pages = "483--487",

booktitle = "2020 IEEE International Conference on Image Processing, ICIP 2020 - Proceedings",

}

TY - GEN

T1 - Adaptive Lattice-Aware Image Demosaicking Using Global and Local Information

AU - Kim, Ji Soo

AU - Ko, Keunsoo

AU - Kim, Chang Su

N1 - Funding Information: This work was supported in part by the MSIT, Korea, under the ITRC support program (IITP-2020-2016-0-00464) supervised by the IITP and in part by the National Research Foundation of Korea (NRF) through the Korea Government (MSIP) under Grant NRF-2018R1A2B3003896. Publisher Copyright: © 2020 IEEE.

PY - 2020/10

Y1 - 2020/10

N2 - A novel approach for image demosaicking based on adaptive lattice-aware filter (ALF) and global refinement unit (GRU) is proposed in this work. We generate ALFs dynamically, which are adaptive to positions of pixels within color lattices in a color filter array, to obtain a locally demosaicked image. We then refine the locally demosaicked image using GRU to exploit global information, as well as local information. To extend the receptive fields efficiently, we adopt dilated convolutions in GRU. Experimental results demonstrate that the proposed algorithm provides the state-of-the-art performances in standard demosaicking datasets.

AB - A novel approach for image demosaicking based on adaptive lattice-aware filter (ALF) and global refinement unit (GRU) is proposed in this work. We generate ALFs dynamically, which are adaptive to positions of pixels within color lattices in a color filter array, to obtain a locally demosaicked image. We then refine the locally demosaicked image using GRU to exploit global information, as well as local information. To extend the receptive fields efficiently, we adopt dilated convolutions in GRU. Experimental results demonstrate that the proposed algorithm provides the state-of-the-art performances in standard demosaicking datasets.

KW - Bayer pattern

KW - Demosaicking

KW - adaptive filters

KW - convolutional neural networks

UR - http://www.scopus.com/inward/record.url?scp=85098617306&partnerID=8YFLogxK

U2 - 10.1109/ICIP40778.2020.9190936

DO - 10.1109/ICIP40778.2020.9190936

M3 - Conference contribution

AN - SCOPUS:85098617306

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 483

EP - 487

BT - 2020 IEEE International Conference on Image Processing, ICIP 2020 - Proceedings

PB - IEEE Computer Society

T2 - 2020 IEEE International Conference on Image Processing, ICIP 2020

Y2 - 25 September 2020 through 28 September 2020

ER -

Adaptive Lattice-Aware Image Demosaicking Using Global and Local Information

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this