3D Scene Parsing via Class-Wise Adaptation

We propose the method that uses only computer graphics datasets to parse the real world 3D scenes. 3D scene parsing based on semantic segmentation is required to implement the categorical interaction in the virtual world. Convolutional Neural Networks (CNNs) have recently shown state-of-theart perfo...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2019-03
Hauptverfasser: Ono, Daichi, Yabe, Hiroyuki, Horikawa, Tsutomu
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Ono, Daichi
Yabe, Hiroyuki
Horikawa, Tsutomu
description We propose the method that uses only computer graphics datasets to parse the real world 3D scenes. 3D scene parsing based on semantic segmentation is required to implement the categorical interaction in the virtual world. Convolutional Neural Networks (CNNs) have recently shown state-of-theart performance on computer vision tasks including semantic segmentation. However, collecting and annotating a huge amount of data are needed to train CNNs. Especially in the case of semantic segmentation, annotating pixel by pixel takes a significant amount of time and often makes mistakes. In contrast, computer graphics can generate a lot of accurate annotated data and easily scale up by changing camera positions, textures and lights. Despite these advantages, models trained on computer graphics datasets cannot perform well on real data, which is known as the domain shift. To address this issue, we first present that depth modal and synthetic noise are effective to reduce the domain shift. Then, we develop the class-wise adaptation which obtains domain invariant features of CNNs. To reduce the domain shift, we create computer graphics rooms with a lot of props, and provide photo-realistic rendered images.We also demonstrate the application which is combined semantic segmentation with Simultaneous Localization and Mapping (SLAM). Our application performs accurate 3D scene parsing in real-time on an actual room.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2154455920</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2154455920</sourcerecordid><originalsourceid>FETCH-proquest_journals_21544559203</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mTQMnZRCE5OzUtVCEgsKs7MS1coy0xUcM5JLC7WDc8sTlVwTEksKEksyczP42FgTUvMKU7lhdLcDMpuriHOHroFRfmFpanFJfFZ-aVFeUCpeCNDUxMTU1NLIwNj4lQBAJQZL9I</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2154455920</pqid></control><display><type>article</type><title>3D Scene Parsing via Class-Wise Adaptation</title><source>Free E- Journals</source><creator>Ono, Daichi ; Yabe, Hiroyuki ; Horikawa, Tsutomu</creator><creatorcontrib>Ono, Daichi ; Yabe, Hiroyuki ; Horikawa, Tsutomu</creatorcontrib><description>We propose the method that uses only computer graphics datasets to parse the real world 3D scenes. 3D scene parsing based on semantic segmentation is required to implement the categorical interaction in the virtual world. Convolutional Neural Networks (CNNs) have recently shown state-of-theart performance on computer vision tasks including semantic segmentation. However, collecting and annotating a huge amount of data are needed to train CNNs. Especially in the case of semantic segmentation, annotating pixel by pixel takes a significant amount of time and often makes mistakes. In contrast, computer graphics can generate a lot of accurate annotated data and easily scale up by changing camera positions, textures and lights. Despite these advantages, models trained on computer graphics datasets cannot perform well on real data, which is known as the domain shift. To address this issue, we first present that depth modal and synthetic noise are effective to reduce the domain shift. Then, we develop the class-wise adaptation which obtains domain invariant features of CNNs. To reduce the domain shift, we create computer graphics rooms with a lot of props, and provide photo-realistic rendered images.We also demonstrate the application which is combined semantic segmentation with Simultaneous Localization and Mapping (SLAM). Our application performs accurate 3D scene parsing in real-time on an actual room.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Adaptation ; Artificial neural networks ; Computer graphics ; Computer vision ; Datasets ; Image segmentation ; Noise reduction ; Pixels ; Semantics ; Simultaneous localization and mapping ; Virtual networks</subject><ispartof>arXiv.org, 2019-03</ispartof><rights>2019. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</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>776,780</link.rule.ids></links><search><creatorcontrib>Ono, Daichi</creatorcontrib><creatorcontrib>Yabe, Hiroyuki</creatorcontrib><creatorcontrib>Horikawa, Tsutomu</creatorcontrib><title>3D Scene Parsing via Class-Wise Adaptation</title><title>arXiv.org</title><description>We propose the method that uses only computer graphics datasets to parse the real world 3D scenes. 3D scene parsing based on semantic segmentation is required to implement the categorical interaction in the virtual world. Convolutional Neural Networks (CNNs) have recently shown state-of-theart performance on computer vision tasks including semantic segmentation. However, collecting and annotating a huge amount of data are needed to train CNNs. Especially in the case of semantic segmentation, annotating pixel by pixel takes a significant amount of time and often makes mistakes. In contrast, computer graphics can generate a lot of accurate annotated data and easily scale up by changing camera positions, textures and lights. Despite these advantages, models trained on computer graphics datasets cannot perform well on real data, which is known as the domain shift. To address this issue, we first present that depth modal and synthetic noise are effective to reduce the domain shift. Then, we develop the class-wise adaptation which obtains domain invariant features of CNNs. To reduce the domain shift, we create computer graphics rooms with a lot of props, and provide photo-realistic rendered images.We also demonstrate the application which is combined semantic segmentation with Simultaneous Localization and Mapping (SLAM). Our application performs accurate 3D scene parsing in real-time on an actual room.</description><subject>Adaptation</subject><subject>Artificial neural networks</subject><subject>Computer graphics</subject><subject>Computer vision</subject><subject>Datasets</subject><subject>Image segmentation</subject><subject>Noise reduction</subject><subject>Pixels</subject><subject>Semantics</subject><subject>Simultaneous localization and mapping</subject><subject>Virtual networks</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mTQMnZRCE5OzUtVCEgsKs7MS1coy0xUcM5JLC7WDc8sTlVwTEksKEksyczP42FgTUvMKU7lhdLcDMpuriHOHroFRfmFpanFJfFZ-aVFeUCpeCNDUxMTU1NLIwNj4lQBAJQZL9I</recordid><startdate>20190301</startdate><enddate>20190301</enddate><creator>Ono, Daichi</creator><creator>Yabe, Hiroyuki</creator><creator>Horikawa, Tsutomu</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20190301</creationdate><title>3D Scene Parsing via Class-Wise Adaptation</title><author>Ono, Daichi ; Yabe, Hiroyuki ; Horikawa, Tsutomu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_21544559203</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Adaptation</topic><topic>Artificial neural networks</topic><topic>Computer graphics</topic><topic>Computer vision</topic><topic>Datasets</topic><topic>Image segmentation</topic><topic>Noise reduction</topic><topic>Pixels</topic><topic>Semantics</topic><topic>Simultaneous localization and mapping</topic><topic>Virtual networks</topic><toplevel>online_resources</toplevel><creatorcontrib>Ono, Daichi</creatorcontrib><creatorcontrib>Yabe, Hiroyuki</creatorcontrib><creatorcontrib>Horikawa, Tsutomu</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ono, Daichi</au><au>Yabe, Hiroyuki</au><au>Horikawa, Tsutomu</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>3D Scene Parsing via Class-Wise Adaptation</atitle><jtitle>arXiv.org</jtitle><date>2019-03-01</date><risdate>2019</risdate><eissn>2331-8422</eissn><abstract>We propose the method that uses only computer graphics datasets to parse the real world 3D scenes. 3D scene parsing based on semantic segmentation is required to implement the categorical interaction in the virtual world. Convolutional Neural Networks (CNNs) have recently shown state-of-theart performance on computer vision tasks including semantic segmentation. However, collecting and annotating a huge amount of data are needed to train CNNs. Especially in the case of semantic segmentation, annotating pixel by pixel takes a significant amount of time and often makes mistakes. In contrast, computer graphics can generate a lot of accurate annotated data and easily scale up by changing camera positions, textures and lights. Despite these advantages, models trained on computer graphics datasets cannot perform well on real data, which is known as the domain shift. To address this issue, we first present that depth modal and synthetic noise are effective to reduce the domain shift. Then, we develop the class-wise adaptation which obtains domain invariant features of CNNs. To reduce the domain shift, we create computer graphics rooms with a lot of props, and provide photo-realistic rendered images.We also demonstrate the application which is combined semantic segmentation with Simultaneous Localization and Mapping (SLAM). Our application performs accurate 3D scene parsing in real-time on an actual room.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2019-03
issn 2331-8422
language eng
recordid cdi_proquest_journals_2154455920
source Free E- Journals
subjects Adaptation
Artificial neural networks
Computer graphics
Computer vision
Datasets
Image segmentation
Noise reduction
Pixels
Semantics
Simultaneous localization and mapping
Virtual networks
title 3D Scene Parsing via Class-Wise Adaptation
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-09T04%3A27%3A06IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=3D%20Scene%20Parsing%20via%20Class-Wise%20Adaptation&rft.jtitle=arXiv.org&rft.au=Ono,%20Daichi&rft.date=2019-03-01&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2154455920%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2154455920&rft_id=info:pmid/&rfr_iscdi=true