Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing

Generative 3D part assembly involves understanding part relationships and predicting their 6-DoF poses for assembling a realistic 3D shape. Prior work often focus on the geometry of individual parts, neglecting part-whole hierarchies of objects. Leveraging two key observations: 1) super-part poses p...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2024-03
Hauptverfasser: Du, Bi'an, Gao, Xiang, Hu, Wei, Liao, Renjie
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 Du, Bi'an
Gao, Xiang
Hu, Wei
Liao, Renjie
description Generative 3D part assembly involves understanding part relationships and predicting their 6-DoF poses for assembling a realistic 3D shape. Prior work often focus on the geometry of individual parts, neglecting part-whole hierarchies of objects. Leveraging two key observations: 1) super-part poses provide strong hints about part poses, and 2) predicting super-part poses is easier due to fewer superparts, we propose a part-whole-hierarchy message passing network for efficient 3D part assembly. We first introduce super-parts by grouping geometrically similar parts without any semantic labels. Then we employ a part-whole hierarchical encoder, wherein a super-part encoder predicts latent super-part poses based on input parts. Subsequently, we transform the point cloud using the latent poses, feeding it to the part encoder for aggregating super-part information and reasoning about part relationships to predict all part poses. In training, only ground-truth part poses are required. During inference, the predicted latent poses of super-parts enhance interpretability. Experimental results on the PartNet dataset show that our method achieves state-of-the-art performance in part and connectivity accuracy and enables an interpretable hierarchical part assembly. Code is available at https://github.com/pkudba/3DHPA.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2932603519</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2932603519</sourcerecordid><originalsourceid>FETCH-proquest_journals_29326035193</originalsourceid><addsrcrecordid>eNqNisEKgkAUAJcgSMp_WOi8sL6XlsfIykvQIegoW7x0xbT2qeDfJ9EHdBqYmYnwADFQmxXATPjMpdYaojWEIXoiOVJNzrS2J4mJPBvXyi0zPW_VIHtrvkZdi6YildrxdPdikCdiNjmNkdnW-UJMH6Zi8n-ci-Vhf9ml6uWad0fcZmXTuXpMGcQIkcYwiPG_6wPKODm6</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2932603519</pqid></control><display><type>article</type><title>Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing</title><source>Free E- Journals</source><creator>Du, Bi'an ; Gao, Xiang ; Hu, Wei ; Liao, Renjie</creator><creatorcontrib>Du, Bi'an ; Gao, Xiang ; Hu, Wei ; Liao, Renjie</creatorcontrib><description>Generative 3D part assembly involves understanding part relationships and predicting their 6-DoF poses for assembling a realistic 3D shape. Prior work often focus on the geometry of individual parts, neglecting part-whole hierarchies of objects. Leveraging two key observations: 1) super-part poses provide strong hints about part poses, and 2) predicting super-part poses is easier due to fewer superparts, we propose a part-whole-hierarchy message passing network for efficient 3D part assembly. We first introduce super-parts by grouping geometrically similar parts without any semantic labels. Then we employ a part-whole hierarchical encoder, wherein a super-part encoder predicts latent super-part poses based on input parts. Subsequently, we transform the point cloud using the latent poses, feeding it to the part encoder for aggregating super-part information and reasoning about part relationships to predict all part poses. In training, only ground-truth part poses are required. During inference, the predicted latent poses of super-parts enhance interpretability. Experimental results on the PartNet dataset show that our method achieves state-of-the-art performance in part and connectivity accuracy and enables an interpretable hierarchical part assembly. Code is available at https://github.com/pkudba/3DHPA.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Assembling ; Assembly ; Coders ; Hierarchies ; Message passing</subject><ispartof>arXiv.org, 2024-03</ispartof><rights>2024. 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>Du, Bi'an</creatorcontrib><creatorcontrib>Gao, Xiang</creatorcontrib><creatorcontrib>Hu, Wei</creatorcontrib><creatorcontrib>Liao, Renjie</creatorcontrib><title>Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing</title><title>arXiv.org</title><description>Generative 3D part assembly involves understanding part relationships and predicting their 6-DoF poses for assembling a realistic 3D shape. Prior work often focus on the geometry of individual parts, neglecting part-whole hierarchies of objects. Leveraging two key observations: 1) super-part poses provide strong hints about part poses, and 2) predicting super-part poses is easier due to fewer superparts, we propose a part-whole-hierarchy message passing network for efficient 3D part assembly. We first introduce super-parts by grouping geometrically similar parts without any semantic labels. Then we employ a part-whole hierarchical encoder, wherein a super-part encoder predicts latent super-part poses based on input parts. Subsequently, we transform the point cloud using the latent poses, feeding it to the part encoder for aggregating super-part information and reasoning about part relationships to predict all part poses. In training, only ground-truth part poses are required. During inference, the predicted latent poses of super-parts enhance interpretability. Experimental results on the PartNet dataset show that our method achieves state-of-the-art performance in part and connectivity accuracy and enables an interpretable hierarchical part assembly. Code is available at https://github.com/pkudba/3DHPA.</description><subject>Assembling</subject><subject>Assembly</subject><subject>Coders</subject><subject>Hierarchies</subject><subject>Message passing</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNisEKgkAUAJcgSMp_WOi8sL6XlsfIykvQIegoW7x0xbT2qeDfJ9EHdBqYmYnwADFQmxXATPjMpdYaojWEIXoiOVJNzrS2J4mJPBvXyi0zPW_VIHtrvkZdi6YildrxdPdikCdiNjmNkdnW-UJMH6Zi8n-ci-Vhf9ml6uWad0fcZmXTuXpMGcQIkcYwiPG_6wPKODm6</recordid><startdate>20240327</startdate><enddate>20240327</enddate><creator>Du, Bi'an</creator><creator>Gao, Xiang</creator><creator>Hu, Wei</creator><creator>Liao, Renjie</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>20240327</creationdate><title>Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing</title><author>Du, Bi'an ; Gao, Xiang ; Hu, Wei ; Liao, Renjie</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_29326035193</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Assembling</topic><topic>Assembly</topic><topic>Coders</topic><topic>Hierarchies</topic><topic>Message passing</topic><toplevel>online_resources</toplevel><creatorcontrib>Du, Bi'an</creatorcontrib><creatorcontrib>Gao, Xiang</creatorcontrib><creatorcontrib>Hu, Wei</creatorcontrib><creatorcontrib>Liao, Renjie</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 (ProQuest)</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>Du, Bi'an</au><au>Gao, Xiang</au><au>Hu, Wei</au><au>Liao, Renjie</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing</atitle><jtitle>arXiv.org</jtitle><date>2024-03-27</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>Generative 3D part assembly involves understanding part relationships and predicting their 6-DoF poses for assembling a realistic 3D shape. Prior work often focus on the geometry of individual parts, neglecting part-whole hierarchies of objects. Leveraging two key observations: 1) super-part poses provide strong hints about part poses, and 2) predicting super-part poses is easier due to fewer superparts, we propose a part-whole-hierarchy message passing network for efficient 3D part assembly. We first introduce super-parts by grouping geometrically similar parts without any semantic labels. Then we employ a part-whole hierarchical encoder, wherein a super-part encoder predicts latent super-part poses based on input parts. Subsequently, we transform the point cloud using the latent poses, feeding it to the part encoder for aggregating super-part information and reasoning about part relationships to predict all part poses. In training, only ground-truth part poses are required. During inference, the predicted latent poses of super-parts enhance interpretability. Experimental results on the PartNet dataset show that our method achieves state-of-the-art performance in part and connectivity accuracy and enables an interpretable hierarchical part assembly. Code is available at https://github.com/pkudba/3DHPA.</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, 2024-03
issn 2331-8422
language eng
recordid cdi_proquest_journals_2932603519
source Free E- Journals
subjects Assembling
Assembly
Coders
Hierarchies
Message passing
title Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-24T01%3A22%3A18IST&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=Generative%203D%20Part%20Assembly%20via%20Part-Whole-Hierarchy%20Message%20Passing&rft.jtitle=arXiv.org&rft.au=Du,%20Bi'an&rft.date=2024-03-27&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2932603519%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2932603519&rft_id=info:pmid/&rfr_iscdi=true