Loading…
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...
Saved in:
Main Authors: | , , , , , |
---|---|
Format: | Conference Proceeding |
Language: | English |
Subjects: | |
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 |