Face super-resolution based on multi-source references

Rui Wang; Muwei Jian; Paul Smith; Hui Yu

doi:10.1109/HSI55341.2022.9869471

Face super-resolution based on multi-source references

Rui Wang, Muwei Jian, Paul Smith, Hui Yu

School of Criminology and Criminal Justice

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

128 Downloads (Pure)

Abstract

This paper proposes a multi-source references (MSR) based face super-resolution (FSR) model. More specifically, to enhance the low-quality large-scale reconstruction of faces without the involvement of face prior knowledge, we propose a multi-source references based FSR framework exploiting a constructed reference library of nonidentity faces and an information mining module for external and internal references. Experimental results show that the proposed model can provide more satisfactory and reliable face super-resolution results than the-state-of-the-art methods.

Original language	English
Title of host publication	2022 15th International Conference on Human System Interaction (HSI)
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1-5
Number of pages	5
ISBN (Electronic)	9781665468220
ISBN (Print)	9781665468237
DOIs	https://doi.org/10.1109/HSI55341.2022.9869471
Publication status	Published - 30 Aug 2022
Event	2022 15th International Conference on Human System Interaction (HSI) - Melbourne, Australia Duration: 28 Jul 2022 → 31 Jul 2022 https://hsi2022.welcometohsi.org/

Publication series

Name	2022 15th International Conference on Human System Interaction (HSI)
Publisher	IEEE
ISSN (Print)	2158-2246
ISSN (Electronic)	2158-2254

Conference

Conference	2022 15th International Conference on Human System Interaction (HSI)
Country/Territory	Australia
City	Melbourne
Period	28/07/22 → 31/07/22
Internet address	https://hsi2022.welcometohsi.org/

Keywords

multi-source
face super-resolution
prior knowledge

Access to Document

10.1109/HSI55341.2022.9869471

Face Super-resolution Based on Multi-source
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript (Post-print), 576 KB

Cite this

@inproceedings{0fd39cf844a94e89b74648e931761571,

title = "Face super-resolution based on multi-source references",

abstract = "This paper proposes a multi-source references (MSR) based face super-resolution (FSR) model. More specifically, to enhance the low-quality large-scale reconstruction of faces without the involvement of face prior knowledge, we propose a multi-source references based FSR framework exploiting a constructed reference library of nonidentity faces and an information mining module for external and internal references. Experimental results show that the proposed model can provide more satisfactory and reliable face super-resolution results than the-state-of-the-art methods.",

keywords = "multi-source, face super-resolution, prior knowledge",

author = "Rui Wang and Muwei Jian and Paul Smith and Hui Yu",

year = "2022",

month = aug,

day = "30",

doi = "10.1109/HSI55341.2022.9869471",

language = "English",

isbn = "9781665468237",

series = "2022 15th International Conference on Human System Interaction (HSI)",

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

pages = "1--5",

booktitle = "2022 15th International Conference on Human System Interaction (HSI)",

address = "United States",

note = "2022 15th International Conference on Human System Interaction (HSI) ; Conference date: 28-07-2022 Through 31-07-2022",

url = "https://hsi2022.welcometohsi.org/",

}

Wang, R, Jian, M, Smith, P & Yu, H 2022, Face super-resolution based on multi-source references. in 2022 15th International Conference on Human System Interaction (HSI). 2022 15th International Conference on Human System Interaction (HSI), Institute of Electrical and Electronics Engineers Inc., pp. 1-5, 2022 15th International Conference on Human System Interaction (HSI), Melbourne, Victoria, Australia, 28/07/22. https://doi.org/10.1109/HSI55341.2022.9869471

Face super-resolution based on multi-source references. / Wang, Rui; Jian, Muwei; Smith, Paul et al.
2022 15th International Conference on Human System Interaction (HSI). Institute of Electrical and Electronics Engineers Inc., 2022. p. 1-5 (2022 15th International Conference on Human System Interaction (HSI)).

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

TY - GEN

T1 - Face super-resolution based on multi-source references

AU - Wang, Rui

AU - Jian, Muwei

AU - Smith, Paul

AU - Yu, Hui

PY - 2022/8/30

Y1 - 2022/8/30

N2 - This paper proposes a multi-source references (MSR) based face super-resolution (FSR) model. More specifically, to enhance the low-quality large-scale reconstruction of faces without the involvement of face prior knowledge, we propose a multi-source references based FSR framework exploiting a constructed reference library of nonidentity faces and an information mining module for external and internal references. Experimental results show that the proposed model can provide more satisfactory and reliable face super-resolution results than the-state-of-the-art methods.

AB - This paper proposes a multi-source references (MSR) based face super-resolution (FSR) model. More specifically, to enhance the low-quality large-scale reconstruction of faces without the involvement of face prior knowledge, we propose a multi-source references based FSR framework exploiting a constructed reference library of nonidentity faces and an information mining module for external and internal references. Experimental results show that the proposed model can provide more satisfactory and reliable face super-resolution results than the-state-of-the-art methods.

KW - multi-source

KW - face super-resolution

KW - prior knowledge

UR - https://dblp.org/db/conf/hsi/hsi2022.html#WangJSY22

UR - https://dblp.org/db/conf/hsi/2022

U2 - 10.1109/HSI55341.2022.9869471

DO - 10.1109/HSI55341.2022.9869471

M3 - Conference contribution

SN - 9781665468237

T3 - 2022 15th International Conference on Human System Interaction (HSI)

SP - 1

EP - 5

BT - 2022 15th International Conference on Human System Interaction (HSI)

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2022 15th International Conference on Human System Interaction (HSI)

Y2 - 28 July 2022 through 31 July 2022

ER -

Face super-resolution based on multi-source references

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this