Upright adjustment with graph convolutional networks

Upright adjustment with graph convolutional networks

We present a novel method for the upright adjustment of 360 images. Our network consists of two modules, which are a convolutional neural network (CNN) and a graph convolutional network (GCN). The input 360 images is processed with the CNN for visual feature extraction, and the extracted feature map...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jung, Raehyuk, Cho, Sungmin, Kwon, Junseok
Format: Artikel
Sprache:eng
Schlagworte:
Computer Science - Computer Vision and Pattern Recognition
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Jung, Raehyuk
Cho, Sungmin
Kwon, Junseok
description We present a novel method for the upright adjustment of 360 images. Our network consists of two modules, which are a convolutional neural network (CNN) and a graph convolutional network (GCN). The input 360 images is processed with the CNN for visual feature extraction, and the extracted feature map is converted into a graph that finds a spherical representation of the input. We also introduce a novel loss function to address the issue of discrete probability distributions defined on the surface of a sphere. Experimental results demonstrate that our method outperforms fully connected based methods.
doi_str_mv 10.48550/arxiv.2406.00263
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2406_00263</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2406_00263</sourcerecordid><originalsourceid>FETCH-arxiv_primary_2406_002633</originalsourceid><addsrcrecordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMjEw0zMwMDIz5mQwCS0oykzPKFFITMkqLS7JTc0rUSjPLMlQSC9KLMhQSM7PK8vPKS3JzM9LzFHISy0pzy_KLuZhYE1LzClO5YXS3Azybq4hzh66YPPjgSbmJhZVxoPsiQfbY0xYBQCa2zNH</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Upright adjustment with graph convolutional networks</title><source>arXiv.org</source><creator>Jung, Raehyuk ; Cho, Sungmin ; Kwon, Junseok</creator><creatorcontrib>Jung, Raehyuk ; Cho, Sungmin ; Kwon, Junseok</creatorcontrib><description>We present a novel method for the upright adjustment of 360 images. Our network consists of two modules, which are a convolutional neural network (CNN) and a graph convolutional network (GCN). The input 360 images is processed with the CNN for visual feature extraction, and the extracted feature map is converted into a graph that finds a spherical representation of the input. We also introduce a novel loss function to address the issue of discrete probability distributions defined on the surface of a sphere. Experimental results demonstrate that our method outperforms fully connected based methods.</description><identifier>DOI: 10.48550/arxiv.2406.00263</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2024-05</creationdate><rights>http://creativecommons.org/licenses/by/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,782,887</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2406.00263$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2406.00263$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Jung, Raehyuk</creatorcontrib><creatorcontrib>Cho, Sungmin</creatorcontrib><creatorcontrib>Kwon, Junseok</creatorcontrib><title>Upright adjustment with graph convolutional networks</title><description>We present a novel method for the upright adjustment of 360 images. Our network consists of two modules, which are a convolutional neural network (CNN) and a graph convolutional network (GCN). The input 360 images is processed with the CNN for visual feature extraction, and the extracted feature map is converted into a graph that finds a spherical representation of the input. We also introduce a novel loss function to address the issue of discrete probability distributions defined on the surface of a sphere. Experimental results demonstrate that our method outperforms fully connected based methods.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNpjYJA0NNAzsTA1NdBPLKrILNMzMjEw0zMwMDIz5mQwCS0oykzPKFFITMkqLS7JTc0rUSjPLMlQSC9KLMhQSM7PK8vPKS3JzM9LzFHISy0pzy_KLuZhYE1LzClO5YXS3Azybq4hzh66YPPjgSbmJhZVxoPsiQfbY0xYBQCa2zNH</recordid><startdate>20240531</startdate><enddate>20240531</enddate><creator>Jung, Raehyuk</creator><creator>Cho, Sungmin</creator><creator>Kwon, Junseok</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20240531</creationdate><title>Upright adjustment with graph convolutional networks</title><author>Jung, Raehyuk ; Cho, Sungmin ; Kwon, Junseok</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-arxiv_primary_2406_002633</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Jung, Raehyuk</creatorcontrib><creatorcontrib>Cho, Sungmin</creatorcontrib><creatorcontrib>Kwon, Junseok</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Jung, Raehyuk</au><au>Cho, Sungmin</au><au>Kwon, Junseok</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Upright adjustment with graph convolutional networks</atitle><date>2024-05-31</date><risdate>2024</risdate><abstract>We present a novel method for the upright adjustment of 360 images. Our network consists of two modules, which are a convolutional neural network (CNN) and a graph convolutional network (GCN). The input 360 images is processed with the CNN for visual feature extraction, and the extracted feature map is converted into a graph that finds a spherical representation of the input. We also introduce a novel loss function to address the issue of discrete probability distributions defined on the surface of a sphere. Experimental results demonstrate that our method outperforms fully connected based methods.</abstract><doi>10.48550/arxiv.2406.00263</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2406.00263
ispartof
issn
language eng
recordid cdi_arxiv_primary_2406_00263
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
title Upright adjustment with graph convolutional networks
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-04T19%3A08%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Upright%20adjustment%20with%20graph%20convolutional%20networks&rft.au=Jung,%20Raehyuk&rft.date=2024-05-31&rft_id=info:doi/10.48550/arxiv.2406.00263&rft_dat=%3Carxiv_GOX%3E2406_00263%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true