Deep Color Mismatch Correction In Stereoscopic 3d Images

Color mismatch in stereoscopic 3D (S3D) images can create visual discomfort and affect the performance of S3D image processing algorithms, e.g., for depth estimation. In this paper, we propose a new deep learning-based solution for the problem of color mismatch correction. The proposed solution cons...

Full description

Saved in:
Bibliographic Details
Main Authors: Croci, Simone, Ozcinar, Cagri, Zerman, Emin, Dudek, Roman, Knorr, Sebastian, Smolic, Aljosa
Format: Conference Proceeding
Language:English
Subjects:
color correction
Color mismatch
convolutional neural network
Image color analysis
Neural networks
Stereo image processing
stereoscopic 3D
Supervised learning
Three-dimensional displays
Training
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 1753
container_issue
container_start_page 1749
container_title
container_volume
creator Croci, Simone
Ozcinar, Cagri
Zerman, Emin
Dudek, Roman
Knorr, Sebastian
Smolic, Aljosa
description Color mismatch in stereoscopic 3D (S3D) images can create visual discomfort and affect the performance of S3D image processing algorithms, e.g., for depth estimation. In this paper, we propose a new deep learning-based solution for the problem of color mismatch correction. The proposed solution consists of a multi-task convolutional neural network, where color correction is the primary task and correspondence estimation is the secondary task. For the training and evaluation of the proposed network, a new S3D image dataset with color mismatch was created. Based on this dataset, experiments were conducted showing the effectiveness of our solution.
doi_str_mv 10.1109/ICIP42928.2021.9506036
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_9506036</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9506036</ieee_id><sourcerecordid>9506036</sourcerecordid><originalsourceid>FETCH-LOGICAL-i203t-58b4d1eaacf277885ed9bfeee53d526f7ddd4bc8c9c56582f470a7660f5ef493</originalsourceid><addsrcrecordid>eNotj81KAzEURqMg2FafQJC8wIy5-ZtkKaPWgYqFdl8yyY1GOp0hmY1vb8GuPs7iHPgIeQRWAzD71LXdVnLLTc0Zh9oqppnQV2QJWispARRckwUXBiqjpL0ly1J-GOMMBCyIeUGcaDsex0w_Uhnc7L_PmDP6OY0n2p3obsaMY_HjlDwVgXaD-8JyR26iOxa8v-yK7N9e9-17tflcd-3zpkqciblSppcB0DkfedMYozDYPiKiEkFxHZsQguy98dYrrQyPsmGu0ZpFhVFasSIP_9l0dg5TToPLv4fLSfEHCIdGpw</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Deep Color Mismatch Correction In Stereoscopic 3d Images</title><source>IEEE Xplore All Conference Series</source><creator>Croci, Simone ; Ozcinar, Cagri ; Zerman, Emin ; Dudek, Roman ; Knorr, Sebastian ; Smolic, Aljosa</creator><creatorcontrib>Croci, Simone ; Ozcinar, Cagri ; Zerman, Emin ; Dudek, Roman ; Knorr, Sebastian ; Smolic, Aljosa</creatorcontrib><description>Color mismatch in stereoscopic 3D (S3D) images can create visual discomfort and affect the performance of S3D image processing algorithms, e.g., for depth estimation. In this paper, we propose a new deep learning-based solution for the problem of color mismatch correction. The proposed solution consists of a multi-task convolutional neural network, where color correction is the primary task and correspondence estimation is the secondary task. For the training and evaluation of the proposed network, a new S3D image dataset with color mismatch was created. Based on this dataset, experiments were conducted showing the effectiveness of our solution.</description><identifier>EISSN: 2381-8549</identifier><identifier>EISBN: 1665441151</identifier><identifier>EISBN: 9781665441155</identifier><identifier>DOI: 10.1109/ICIP42928.2021.9506036</identifier><language>eng</language><publisher>IEEE</publisher><subject>color correction ; Color mismatch ; convolutional neural network ; Image color analysis ; Neural networks ; Stereo image processing ; stereoscopic 3D ; Supervised learning ; Three-dimensional displays ; Training ; Visualization</subject><ispartof>2021 IEEE International Conference on Image Processing (ICIP), 2021, p.1749-1753</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9506036$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,23930,23931,25140,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9506036$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Croci, Simone</creatorcontrib><creatorcontrib>Ozcinar, Cagri</creatorcontrib><creatorcontrib>Zerman, Emin</creatorcontrib><creatorcontrib>Dudek, Roman</creatorcontrib><creatorcontrib>Knorr, Sebastian</creatorcontrib><creatorcontrib>Smolic, Aljosa</creatorcontrib><title>Deep Color Mismatch Correction In Stereoscopic 3d Images</title><title>2021 IEEE International Conference on Image Processing (ICIP)</title><addtitle>ICIP</addtitle><description>Color mismatch in stereoscopic 3D (S3D) images can create visual discomfort and affect the performance of S3D image processing algorithms, e.g., for depth estimation. In this paper, we propose a new deep learning-based solution for the problem of color mismatch correction. The proposed solution consists of a multi-task convolutional neural network, where color correction is the primary task and correspondence estimation is the secondary task. For the training and evaluation of the proposed network, a new S3D image dataset with color mismatch was created. Based on this dataset, experiments were conducted showing the effectiveness of our solution.</description><subject>color correction</subject><subject>Color mismatch</subject><subject>convolutional neural network</subject><subject>Image color analysis</subject><subject>Neural networks</subject><subject>Stereo image processing</subject><subject>stereoscopic 3D</subject><subject>Supervised learning</subject><subject>Three-dimensional displays</subject><subject>Training</subject><subject>Visualization</subject><issn>2381-8549</issn><isbn>1665441151</isbn><isbn>9781665441155</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2021</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj81KAzEURqMg2FafQJC8wIy5-ZtkKaPWgYqFdl8yyY1GOp0hmY1vb8GuPs7iHPgIeQRWAzD71LXdVnLLTc0Zh9oqppnQV2QJWispARRckwUXBiqjpL0ly1J-GOMMBCyIeUGcaDsex0w_Uhnc7L_PmDP6OY0n2p3obsaMY_HjlDwVgXaD-8JyR26iOxa8v-yK7N9e9-17tflcd-3zpkqciblSppcB0DkfedMYozDYPiKiEkFxHZsQguy98dYrrQyPsmGu0ZpFhVFasSIP_9l0dg5TToPLv4fLSfEHCIdGpw</recordid><startdate>20210919</startdate><enddate>20210919</enddate><creator>Croci, Simone</creator><creator>Ozcinar, Cagri</creator><creator>Zerman, Emin</creator><creator>Dudek, Roman</creator><creator>Knorr, Sebastian</creator><creator>Smolic, Aljosa</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>20210919</creationdate><title>Deep Color Mismatch Correction In Stereoscopic 3d Images</title><author>Croci, Simone ; Ozcinar, Cagri ; Zerman, Emin ; Dudek, Roman ; Knorr, Sebastian ; Smolic, Aljosa</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i203t-58b4d1eaacf277885ed9bfeee53d526f7ddd4bc8c9c56582f470a7660f5ef493</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2021</creationdate><topic>color correction</topic><topic>Color mismatch</topic><topic>convolutional neural network</topic><topic>Image color analysis</topic><topic>Neural networks</topic><topic>Stereo image processing</topic><topic>stereoscopic 3D</topic><topic>Supervised learning</topic><topic>Three-dimensional displays</topic><topic>Training</topic><topic>Visualization</topic><toplevel>online_resources</toplevel><creatorcontrib>Croci, Simone</creatorcontrib><creatorcontrib>Ozcinar, Cagri</creatorcontrib><creatorcontrib>Zerman, Emin</creatorcontrib><creatorcontrib>Dudek, Roman</creatorcontrib><creatorcontrib>Knorr, Sebastian</creatorcontrib><creatorcontrib>Smolic, Aljosa</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library Online</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Croci, Simone</au><au>Ozcinar, Cagri</au><au>Zerman, Emin</au><au>Dudek, Roman</au><au>Knorr, Sebastian</au><au>Smolic, Aljosa</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Deep Color Mismatch Correction In Stereoscopic 3d Images</atitle><btitle>2021 IEEE International Conference on Image Processing (ICIP)</btitle><stitle>ICIP</stitle><date>2021-09-19</date><risdate>2021</risdate><spage>1749</spage><epage>1753</epage><pages>1749-1753</pages><eissn>2381-8549</eissn><eisbn>1665441151</eisbn><eisbn>9781665441155</eisbn><abstract>Color mismatch in stereoscopic 3D (S3D) images can create visual discomfort and affect the performance of S3D image processing algorithms, e.g., for depth estimation. In this paper, we propose a new deep learning-based solution for the problem of color mismatch correction. The proposed solution consists of a multi-task convolutional neural network, where color correction is the primary task and correspondence estimation is the secondary task. For the training and evaluation of the proposed network, a new S3D image dataset with color mismatch was created. Based on this dataset, experiments were conducted showing the effectiveness of our solution.</abstract><pub>IEEE</pub><doi>10.1109/ICIP42928.2021.9506036</doi><tpages>5</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2381-8549
ispartof 2021 IEEE International Conference on Image Processing (ICIP), 2021, p.1749-1753
issn 2381-8549
language eng
recordid cdi_ieee_primary_9506036
source IEEE Xplore All Conference Series
subjects color correction
Color mismatch
convolutional neural network
Image color analysis
Neural networks
Stereo image processing
stereoscopic 3D
Supervised learning
Three-dimensional displays
Training
Visualization
title Deep Color Mismatch Correction In Stereoscopic 3d Images
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T11%3A43%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Deep%20Color%20Mismatch%20Correction%20In%20Stereoscopic%203d%20Images&rft.btitle=2021%20IEEE%20International%20Conference%20on%20Image%20Processing%20(ICIP)&rft.au=Croci,%20Simone&rft.date=2021-09-19&rft.spage=1749&rft.epage=1753&rft.pages=1749-1753&rft.eissn=2381-8549&rft_id=info:doi/10.1109/ICIP42928.2021.9506036&rft.eisbn=1665441151&rft.eisbn_list=9781665441155&rft_dat=%3Cieee_CHZPO%3E9506036%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i203t-58b4d1eaacf277885ed9bfeee53d526f7ddd4bc8c9c56582f470a7660f5ef493%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=9506036&rfr_iscdi=true