3DIAS: 3D Shape Reconstruction with Implicit Algebraic Surfaces

3D Shape representation has substantial effects on 3D shape reconstruction. Primitive-based representations approximate a 3D shape mainly by a set of simple implicit primitives, but the low geometrical complexity of the primitives limits the shape resolution. Moreover, setting a sufficient number of...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yavartanoo, Mohsen, Chung, JaeYoung, Neshatavar, Reyhaneh, Lee, Kyoung Mu
Format: Artikel
Sprache:eng
Schlagworte:
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 Yavartanoo, Mohsen
Chung, JaeYoung
Neshatavar, Reyhaneh
Lee, Kyoung Mu
description 3D Shape representation has substantial effects on 3D shape reconstruction. Primitive-based representations approximate a 3D shape mainly by a set of simple implicit primitives, but the low geometrical complexity of the primitives limits the shape resolution. Moreover, setting a sufficient number of primitives for an arbitrary shape is challenging. To overcome these issues, we propose a constrained implicit algebraic surface as the primitive with few learnable coefficients and higher geometrical complexities and a deep neural network to produce these primitives. Our experiments demonstrate the superiorities of our method in terms of representation power compared to the state-of-the-art methods in single RGB image 3D shape reconstruction. Furthermore, we show that our method can semantically learn segments of 3D shapes in an unsupervised manner. The code is publicly available from https://myavartanoo.github.io/3dias/ .
doi_str_mv 10.48550/arxiv.2108.08653
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2108_08653</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2108_08653</sourcerecordid><originalsourceid>FETCH-LOGICAL-a673-75c064ab36e82a30eb14f43329b19d5ac85c45a10007d0acda6692873127da433</originalsourceid><addsrcrecordid>eNotz8lOwzAUhWFvWKDCA7DCL5Bw7espbFDUMkSqhES6j24ch1pK28hJGd4eaFmdza8jfYzdCMiV0xruKH3Fj1wKcDk4o_GSPeCqKut7jiteb2kM_C34w36a09HP8bDnn3He8mo3DtHHmZfDe2gTRc_rY-rJh-mKXfQ0TOH6fxds8_S4Wb5k69fnalmuMzIWM6s9GEUtmuAkIYRWqF4hyqIVRafJO-2VJgEAtgPyHRlTSGdRSNvRb7hgt-fbk6AZU9xR-m7-JM1Jgj-qCkGA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>3DIAS: 3D Shape Reconstruction with Implicit Algebraic Surfaces</title><source>arXiv.org</source><creator>Yavartanoo, Mohsen ; Chung, JaeYoung ; Neshatavar, Reyhaneh ; Lee, Kyoung Mu</creator><creatorcontrib>Yavartanoo, Mohsen ; Chung, JaeYoung ; Neshatavar, Reyhaneh ; Lee, Kyoung Mu</creatorcontrib><description>3D Shape representation has substantial effects on 3D shape reconstruction. Primitive-based representations approximate a 3D shape mainly by a set of simple implicit primitives, but the low geometrical complexity of the primitives limits the shape resolution. Moreover, setting a sufficient number of primitives for an arbitrary shape is challenging. To overcome these issues, we propose a constrained implicit algebraic surface as the primitive with few learnable coefficients and higher geometrical complexities and a deep neural network to produce these primitives. Our experiments demonstrate the superiorities of our method in terms of representation power compared to the state-of-the-art methods in single RGB image 3D shape reconstruction. Furthermore, we show that our method can semantically learn segments of 3D shapes in an unsupervised manner. The code is publicly available from https://myavartanoo.github.io/3dias/ .</description><identifier>DOI: 10.48550/arxiv.2108.08653</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2021-08</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>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2108.08653$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2108.08653$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Yavartanoo, Mohsen</creatorcontrib><creatorcontrib>Chung, JaeYoung</creatorcontrib><creatorcontrib>Neshatavar, Reyhaneh</creatorcontrib><creatorcontrib>Lee, Kyoung Mu</creatorcontrib><title>3DIAS: 3D Shape Reconstruction with Implicit Algebraic Surfaces</title><description>3D Shape representation has substantial effects on 3D shape reconstruction. Primitive-based representations approximate a 3D shape mainly by a set of simple implicit primitives, but the low geometrical complexity of the primitives limits the shape resolution. Moreover, setting a sufficient number of primitives for an arbitrary shape is challenging. To overcome these issues, we propose a constrained implicit algebraic surface as the primitive with few learnable coefficients and higher geometrical complexities and a deep neural network to produce these primitives. Our experiments demonstrate the superiorities of our method in terms of representation power compared to the state-of-the-art methods in single RGB image 3D shape reconstruction. Furthermore, we show that our method can semantically learn segments of 3D shapes in an unsupervised manner. The code is publicly available from https://myavartanoo.github.io/3dias/ .</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz8lOwzAUhWFvWKDCA7DCL5Bw7espbFDUMkSqhES6j24ch1pK28hJGd4eaFmdza8jfYzdCMiV0xruKH3Fj1wKcDk4o_GSPeCqKut7jiteb2kM_C34w36a09HP8bDnn3He8mo3DtHHmZfDe2gTRc_rY-rJh-mKXfQ0TOH6fxds8_S4Wb5k69fnalmuMzIWM6s9GEUtmuAkIYRWqF4hyqIVRafJO-2VJgEAtgPyHRlTSGdRSNvRb7hgt-fbk6AZU9xR-m7-JM1Jgj-qCkGA</recordid><startdate>20210819</startdate><enddate>20210819</enddate><creator>Yavartanoo, Mohsen</creator><creator>Chung, JaeYoung</creator><creator>Neshatavar, Reyhaneh</creator><creator>Lee, Kyoung Mu</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20210819</creationdate><title>3DIAS: 3D Shape Reconstruction with Implicit Algebraic Surfaces</title><author>Yavartanoo, Mohsen ; Chung, JaeYoung ; Neshatavar, Reyhaneh ; Lee, Kyoung Mu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a673-75c064ab36e82a30eb14f43329b19d5ac85c45a10007d0acda6692873127da433</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Yavartanoo, Mohsen</creatorcontrib><creatorcontrib>Chung, JaeYoung</creatorcontrib><creatorcontrib>Neshatavar, Reyhaneh</creatorcontrib><creatorcontrib>Lee, Kyoung Mu</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Yavartanoo, Mohsen</au><au>Chung, JaeYoung</au><au>Neshatavar, Reyhaneh</au><au>Lee, Kyoung Mu</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>3DIAS: 3D Shape Reconstruction with Implicit Algebraic Surfaces</atitle><date>2021-08-19</date><risdate>2021</risdate><abstract>3D Shape representation has substantial effects on 3D shape reconstruction. Primitive-based representations approximate a 3D shape mainly by a set of simple implicit primitives, but the low geometrical complexity of the primitives limits the shape resolution. Moreover, setting a sufficient number of primitives for an arbitrary shape is challenging. To overcome these issues, we propose a constrained implicit algebraic surface as the primitive with few learnable coefficients and higher geometrical complexities and a deep neural network to produce these primitives. Our experiments demonstrate the superiorities of our method in terms of representation power compared to the state-of-the-art methods in single RGB image 3D shape reconstruction. Furthermore, we show that our method can semantically learn segments of 3D shapes in an unsupervised manner. The code is publicly available from https://myavartanoo.github.io/3dias/ .</abstract><doi>10.48550/arxiv.2108.08653</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2108.08653
ispartof
issn
language eng
recordid cdi_arxiv_primary_2108_08653
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
title 3DIAS: 3D Shape Reconstruction with Implicit Algebraic Surfaces
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T03%3A26%3A46IST&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=3DIAS:%203D%20Shape%20Reconstruction%20with%20Implicit%20Algebraic%20Surfaces&rft.au=Yavartanoo,%20Mohsen&rft.date=2021-08-19&rft_id=info:doi/10.48550/arxiv.2108.08653&rft_dat=%3Carxiv_GOX%3E2108_08653%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