Deep Image Fusion Accounting for Inter-Image Variability

Xiuheng Wang; Ricardo Augusto Borsoi; Cedric Richard; Jie Chen

doi:10.1109/IEEECONF56349.2022.10051954

Deep Image Fusion Accounting for Inter-Image Variability

Xiuheng Wang, Ricardo Augusto Borsoi, Cedric Richard, Jie Chen

School of Marine Science and Technology

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

1 Scopus citations

Abstract

Hyperspectral and multispectral image fusion (HMIF) allows us to overcome inherent hardware limitations of hyperspectral imaging systems with respect to their lower spatial resolution. However, existing algorithms fail to consider realistic image acquisition conditions, or to leverage the powerful representation capacity of deep neural networks. This paper introduces a general imaging model which considers inter-image variabil-ity of data from heterogeneous sources, and formulates the optimization problem. Then it presents a new image fusion method that, on the one hand, solves the optimization prob-lem accounting for inter-image variability with an iteratively reweighted scheme and, on the other hand, leverages unsu-pervised light-weight CNN-based denoisers to learn realistic image priors from data. Its performance is illustrated with real data that suffer from inter-image variability.

Original language	English
Title of host publication	56th Asilomar Conference on Signals, Systems and Computers, ACSSC 2022
Editors	Michael B. Matthews
Publisher	IEEE Computer Society
Pages	645-649
Number of pages	5
ISBN (Electronic)	9781665459068
DOIs	https://doi.org/10.1109/IEEECONF56349.2022.10051954
State	Published - 2022
Event	56th Asilomar Conference on Signals, Systems and Computers, ACSSC 2022 - Virtual, Online, United States Duration: 31 Oct 2022 → 2 Nov 2022

Publication series

Name	Conference Record - Asilomar Conference on Signals, Systems and Computers
Volume	2022-October
ISSN (Print)	1058-6393

Conference

Conference	56th Asilomar Conference on Signals, Systems and Computers, ACSSC 2022
Country/Territory	United States
City	Virtual, Online
Period	31/10/22 → 2/11/22

Keywords

deep learning
Hyperspectral data
image fusion
inter-image variability
multispectral data

Access to Document

10.1109/IEEECONF56349.2022.10051954

Cite this

Wang, X., Borsoi, R. A., Richard, C., & Chen, J. (2022). Deep Image Fusion Accounting for Inter-Image Variability. In M. B. Matthews (Ed.), 56th Asilomar Conference on Signals, Systems and Computers, ACSSC 2022 (pp. 645-649). (Conference Record - Asilomar Conference on Signals, Systems and Computers; Vol. 2022-October). IEEE Computer Society. https://doi.org/10.1109/IEEECONF56349.2022.10051954

@inproceedings{9cb197ce52734b8293e3d3c4e699419e,

title = "Deep Image Fusion Accounting for Inter-Image Variability",

abstract = "Hyperspectral and multispectral image fusion (HMIF) allows us to overcome inherent hardware limitations of hyperspectral imaging systems with respect to their lower spatial resolution. However, existing algorithms fail to consider realistic image acquisition conditions, or to leverage the powerful representation capacity of deep neural networks. This paper introduces a general imaging model which considers inter-image variabil-ity of data from heterogeneous sources, and formulates the optimization problem. Then it presents a new image fusion method that, on the one hand, solves the optimization prob-lem accounting for inter-image variability with an iteratively reweighted scheme and, on the other hand, leverages unsu-pervised light-weight CNN-based denoisers to learn realistic image priors from data. Its performance is illustrated with real data that suffer from inter-image variability.",

keywords = "deep learning, Hyperspectral data, image fusion, inter-image variability, multispectral data",

author = "Xiuheng Wang and Borsoi, {Ricardo Augusto} and Cedric Richard and Jie Chen",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 56th Asilomar Conference on Signals, Systems and Computers, ACSSC 2022 ; Conference date: 31-10-2022 Through 02-11-2022",

year = "2022",

doi = "10.1109/IEEECONF56349.2022.10051954",

language = "英语",

series = "Conference Record - Asilomar Conference on Signals, Systems and Computers",

publisher = "IEEE Computer Society",

pages = "645--649",

editor = "Matthews, {Michael B.}",

booktitle = "56th Asilomar Conference on Signals, Systems and Computers, ACSSC 2022",

}

Wang, X, Borsoi, RA, Richard, C & Chen, J 2022, Deep Image Fusion Accounting for Inter-Image Variability. in MB Matthews (ed.), 56th Asilomar Conference on Signals, Systems and Computers, ACSSC 2022. Conference Record - Asilomar Conference on Signals, Systems and Computers, vol. 2022-October, IEEE Computer Society, pp. 645-649, 56th Asilomar Conference on Signals, Systems and Computers, ACSSC 2022, Virtual, Online, United States, 31/10/22. https://doi.org/10.1109/IEEECONF56349.2022.10051954

Deep Image Fusion Accounting for Inter-Image Variability. / Wang, Xiuheng; Borsoi, Ricardo Augusto; Richard, Cedric et al.
56th Asilomar Conference on Signals, Systems and Computers, ACSSC 2022. ed. / Michael B. Matthews. IEEE Computer Society, 2022. p. 645-649 (Conference Record - Asilomar Conference on Signals, Systems and Computers; Vol. 2022-October).

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

TY - GEN

T1 - Deep Image Fusion Accounting for Inter-Image Variability

AU - Wang, Xiuheng

AU - Borsoi, Ricardo Augusto

AU - Richard, Cedric

AU - Chen, Jie

PY - 2022

Y1 - 2022

N2 - Hyperspectral and multispectral image fusion (HMIF) allows us to overcome inherent hardware limitations of hyperspectral imaging systems with respect to their lower spatial resolution. However, existing algorithms fail to consider realistic image acquisition conditions, or to leverage the powerful representation capacity of deep neural networks. This paper introduces a general imaging model which considers inter-image variabil-ity of data from heterogeneous sources, and formulates the optimization problem. Then it presents a new image fusion method that, on the one hand, solves the optimization prob-lem accounting for inter-image variability with an iteratively reweighted scheme and, on the other hand, leverages unsu-pervised light-weight CNN-based denoisers to learn realistic image priors from data. Its performance is illustrated with real data that suffer from inter-image variability.

AB - Hyperspectral and multispectral image fusion (HMIF) allows us to overcome inherent hardware limitations of hyperspectral imaging systems with respect to their lower spatial resolution. However, existing algorithms fail to consider realistic image acquisition conditions, or to leverage the powerful representation capacity of deep neural networks. This paper introduces a general imaging model which considers inter-image variabil-ity of data from heterogeneous sources, and formulates the optimization problem. Then it presents a new image fusion method that, on the one hand, solves the optimization prob-lem accounting for inter-image variability with an iteratively reweighted scheme and, on the other hand, leverages unsu-pervised light-weight CNN-based denoisers to learn realistic image priors from data. Its performance is illustrated with real data that suffer from inter-image variability.

KW - deep learning

KW - Hyperspectral data

KW - image fusion

KW - inter-image variability

KW - multispectral data

UR - http://www.scopus.com/inward/record.url?scp=85150162455&partnerID=8YFLogxK

U2 - 10.1109/IEEECONF56349.2022.10051954

DO - 10.1109/IEEECONF56349.2022.10051954

M3 - 会议稿件

AN - SCOPUS:85150162455

T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers

SP - 645

EP - 649

BT - 56th Asilomar Conference on Signals, Systems and Computers, ACSSC 2022

A2 - Matthews, Michael B.

PB - IEEE Computer Society

T2 - 56th Asilomar Conference on Signals, Systems and Computers, ACSSC 2022

Y2 - 31 October 2022 through 2 November 2022

ER -

Deep Image Fusion Accounting for Inter-Image Variability

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this