CollageNet: Face Super-Resolution Using Reference Images

Ji Soo Kim; Chang Su Kim

doi:10.1109/ITC-CSCC55581.2022.9894910

CollageNet: Face Super-Resolution Using Reference Images

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

Abstract

A novel approach to face super-resolution (SR) using reference images, called CollageNet, is described in this paper. First, we extract features and reorganize them into patches. Next, we compute the similarity between input and reference patches and select the most similar reference patch to each input patch. We then compose a collaged feature using such selected reference patches. Finally, we blend both input and collaged features to obtain an SR image. Experimental results demonstrate that CollageNet provides excellent performance.

Original language	English
Title of host publication	ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	916-917
Number of pages	2
ISBN (Electronic)	9781665485593
DOIs	https://doi.org/10.1109/ITC-CSCC55581.2022.9894910
Publication status	Published - 2022
Event	37th International Technical Conference on Circuits/Systems, Computers and Communications, ITC-CSCC 2022 - Phuket, Thailand Duration: 2022 Jul 5 → 2022 Jul 8

Publication series

Name	ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications

Conference

Conference	37th International Technical Conference on Circuits/Systems, Computers and Communications, ITC-CSCC 2022
Country/Territory	Thailand
City	Phuket
Period	22/7/5 → 22/7/8

Bibliographical note

Funding Information:
ACKNOWLEDGMENT This work was supported by the National Research Foundation of Korea (NRF) grants funded by the Korea government (MSIT) (No. NRF-2021R1A4A1031864 and No. NRF-2022R1A2B5B03002310).

Publisher Copyright:
© 2022 IEEE.

Keywords

convolutional neural network
Face super-resolution
reference based super-resolution

ASJC Scopus subject areas

Information Systems
Electrical and Electronic Engineering
Artificial Intelligence
Computer Networks and Communications
Computer Science Applications
Hardware and Architecture

Access to Document

10.1109/ITC-CSCC55581.2022.9894910

Cite this

Kim, J. S., & Kim, C. S. (2022). CollageNet: Face Super-Resolution Using Reference Images. In ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications (pp. 916-917). (ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ITC-CSCC55581.2022.9894910

CollageNet: Face Super-Resolution Using Reference Images. / Kim, Ji Soo; Kim, Chang Su.
ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications. Institute of Electrical and Electronics Engineers Inc., 2022. p. 916-917 (ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications).

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

Kim, JS & Kim, CS 2022, CollageNet: Face Super-Resolution Using Reference Images. in ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications. ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications, Institute of Electrical and Electronics Engineers Inc., pp. 916-917, 37th International Technical Conference on Circuits/Systems, Computers and Communications, ITC-CSCC 2022, Phuket, Thailand, 22/7/5. https://doi.org/10.1109/ITC-CSCC55581.2022.9894910

Kim JS, Kim CS. CollageNet: Face Super-Resolution Using Reference Images. In ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications. Institute of Electrical and Electronics Engineers Inc. 2022. p. 916-917. (ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications). doi: 10.1109/ITC-CSCC55581.2022.9894910

Kim, Ji Soo ; Kim, Chang Su. / CollageNet : Face Super-Resolution Using Reference Images. ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 916-917 (ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications).

@inproceedings{3ea929c1d529481db6e81260c8f7c3b9,

title = "CollageNet: Face Super-Resolution Using Reference Images",

abstract = "A novel approach to face super-resolution (SR) using reference images, called CollageNet, is described in this paper. First, we extract features and reorganize them into patches. Next, we compute the similarity between input and reference patches and select the most similar reference patch to each input patch. We then compose a collaged feature using such selected reference patches. Finally, we blend both input and collaged features to obtain an SR image. Experimental results demonstrate that CollageNet provides excellent performance.",

keywords = "convolutional neural network, Face super-resolution, reference based super-resolution",

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

note = "Funding Information: ACKNOWLEDGMENT This work was supported by the National Research Foundation of Korea (NRF) grants funded by the Korea government (MSIT) (No. NRF-2021R1A4A1031864 and No. NRF-2022R1A2B5B03002310). Publisher Copyright: {\textcopyright} 2022 IEEE.; 37th International Technical Conference on Circuits/Systems, Computers and Communications, ITC-CSCC 2022 ; Conference date: 05-07-2022 Through 08-07-2022",

year = "2022",

doi = "10.1109/ITC-CSCC55581.2022.9894910",

language = "English",

series = "ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications",

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

pages = "916--917",

booktitle = "ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications",

}

TY - GEN

T1 - CollageNet

T2 - 37th International Technical Conference on Circuits/Systems, Computers and Communications, ITC-CSCC 2022

AU - Kim, Ji Soo

AU - Kim, Chang Su

N1 - Funding Information: ACKNOWLEDGMENT This work was supported by the National Research Foundation of Korea (NRF) grants funded by the Korea government (MSIT) (No. NRF-2021R1A4A1031864 and No. NRF-2022R1A2B5B03002310). Publisher Copyright: © 2022 IEEE.

PY - 2022

Y1 - 2022

N2 - A novel approach to face super-resolution (SR) using reference images, called CollageNet, is described in this paper. First, we extract features and reorganize them into patches. Next, we compute the similarity between input and reference patches and select the most similar reference patch to each input patch. We then compose a collaged feature using such selected reference patches. Finally, we blend both input and collaged features to obtain an SR image. Experimental results demonstrate that CollageNet provides excellent performance.

AB - A novel approach to face super-resolution (SR) using reference images, called CollageNet, is described in this paper. First, we extract features and reorganize them into patches. Next, we compute the similarity between input and reference patches and select the most similar reference patch to each input patch. We then compose a collaged feature using such selected reference patches. Finally, we blend both input and collaged features to obtain an SR image. Experimental results demonstrate that CollageNet provides excellent performance.

KW - convolutional neural network

KW - Face super-resolution

KW - reference based super-resolution

UR - http://www.scopus.com/inward/record.url?scp=85140615963&partnerID=8YFLogxK

U2 - 10.1109/ITC-CSCC55581.2022.9894910

DO - 10.1109/ITC-CSCC55581.2022.9894910

M3 - Conference contribution

AN - SCOPUS:85140615963

T3 - ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications

SP - 916

EP - 917

BT - ITC-CSCC 2022 - 37th International Technical Conference on Circuits/Systems, Computers and Communications

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 5 July 2022 through 8 July 2022

ER -

CollageNet: Face Super-Resolution Using Reference Images

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this