Novel 3D Scene Understanding Applications From Recurrence in a Single Image

Novel 3D Scene Understanding Applications From Recurrence in a Single Image

We demonstrate the utility of recurring pattern discovery from a single image for spatial understanding of a 3D scene in terms of (1) vanishing point detection, (2) hypothesizing 3D translation symmetry and (3) counting the number of RP instances in the image. Furthermore, we illustrate the feasibil...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Shimian, Bharadwaj, Skanda, Kraiger, Keaton, Asthana, Yashasvi, Zhang, Hong, Collins, Robert, Liu, Yanxi
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 Zhang, Shimian
Bharadwaj, Skanda
Kraiger, Keaton
Asthana, Yashasvi
Zhang, Hong
Collins, Robert
Liu, Yanxi
description We demonstrate the utility of recurring pattern discovery from a single image for spatial understanding of a 3D scene in terms of (1) vanishing point detection, (2) hypothesizing 3D translation symmetry and (3) counting the number of RP instances in the image. Furthermore, we illustrate the feasibility of leveraging RP discovery output to form a more precise, quantitative text description of the scene. Our quantitative evaluations on a new 1K+ Recurring Pattern (RP) benchmark with diverse variations show that visual perception of recurrence from one single view leads to scene understanding outcomes that are as good as or better than existing supervised methods and/or unsupervised methods that use millions of images.
doi_str_mv 10.48550/arxiv.2210.07991
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2210_07991</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2210_07991</sourcerecordid><originalsourceid>FETCH-LOGICAL-a671-2a276043108cb51c0b9afee4f2e11bbcf565c33e6d83204aa6e9389158d34ca13</originalsourceid><addsrcrecordid>eNotz81Kw0AUBeDZuJDqA7jyvkDq_GdmWarVYlGwdR1uJjdlIJmESS369tba1YHD4cDH2J3gc-2M4Q-Yv-NxLuWp4KX34pq9vg1H6kA9wjZQIvhMDeXpgKmJaQ-LcexiwEMc0gSrPPTwQeErZ0qBICZA2J5mHcG6xz3dsKsWu4luLzlju9XTbvlSbN6f18vFpkBbikKiLC3XSnAXaiMCrz22RLqVJERdh9ZYE5Qi2zgluUa05JXzwrhG6YBCzdj9_-1ZU4059ph_qj9VdVapX_VoRr0</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Novel 3D Scene Understanding Applications From Recurrence in a Single Image</title><source>arXiv.org</source><creator>Zhang, Shimian ; Bharadwaj, Skanda ; Kraiger, Keaton ; Asthana, Yashasvi ; Zhang, Hong ; Collins, Robert ; Liu, Yanxi</creator><creatorcontrib>Zhang, Shimian ; Bharadwaj, Skanda ; Kraiger, Keaton ; Asthana, Yashasvi ; Zhang, Hong ; Collins, Robert ; Liu, Yanxi</creatorcontrib><description>We demonstrate the utility of recurring pattern discovery from a single image for spatial understanding of a 3D scene in terms of (1) vanishing point detection, (2) hypothesizing 3D translation symmetry and (3) counting the number of RP instances in the image. Furthermore, we illustrate the feasibility of leveraging RP discovery output to form a more precise, quantitative text description of the scene. Our quantitative evaluations on a new 1K+ Recurring Pattern (RP) benchmark with diverse variations show that visual perception of recurrence from one single view leads to scene understanding outcomes that are as good as or better than existing supervised methods and/or unsupervised methods that use millions of images.</description><identifier>DOI: 10.48550/arxiv.2210.07991</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition</subject><creationdate>2022-10</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2210.07991$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2210.07991$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Zhang, Shimian</creatorcontrib><creatorcontrib>Bharadwaj, Skanda</creatorcontrib><creatorcontrib>Kraiger, Keaton</creatorcontrib><creatorcontrib>Asthana, Yashasvi</creatorcontrib><creatorcontrib>Zhang, Hong</creatorcontrib><creatorcontrib>Collins, Robert</creatorcontrib><creatorcontrib>Liu, Yanxi</creatorcontrib><title>Novel 3D Scene Understanding Applications From Recurrence in a Single Image</title><description>We demonstrate the utility of recurring pattern discovery from a single image for spatial understanding of a 3D scene in terms of (1) vanishing point detection, (2) hypothesizing 3D translation symmetry and (3) counting the number of RP instances in the image. Furthermore, we illustrate the feasibility of leveraging RP discovery output to form a more precise, quantitative text description of the scene. Our quantitative evaluations on a new 1K+ Recurring Pattern (RP) benchmark with diverse variations show that visual perception of recurrence from one single view leads to scene understanding outcomes that are as good as or better than existing supervised methods and/or unsupervised methods that use millions of images.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotz81Kw0AUBeDZuJDqA7jyvkDq_GdmWarVYlGwdR1uJjdlIJmESS369tba1YHD4cDH2J3gc-2M4Q-Yv-NxLuWp4KX34pq9vg1H6kA9wjZQIvhMDeXpgKmJaQ-LcexiwEMc0gSrPPTwQeErZ0qBICZA2J5mHcG6xz3dsKsWu4luLzlju9XTbvlSbN6f18vFpkBbikKiLC3XSnAXaiMCrz22RLqVJERdh9ZYE5Qi2zgluUa05JXzwrhG6YBCzdj9_-1ZU4059ph_qj9VdVapX_VoRr0</recordid><startdate>20221014</startdate><enddate>20221014</enddate><creator>Zhang, Shimian</creator><creator>Bharadwaj, Skanda</creator><creator>Kraiger, Keaton</creator><creator>Asthana, Yashasvi</creator><creator>Zhang, Hong</creator><creator>Collins, Robert</creator><creator>Liu, Yanxi</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20221014</creationdate><title>Novel 3D Scene Understanding Applications From Recurrence in a Single Image</title><author>Zhang, Shimian ; Bharadwaj, Skanda ; Kraiger, Keaton ; Asthana, Yashasvi ; Zhang, Hong ; Collins, Robert ; Liu, Yanxi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a671-2a276043108cb51c0b9afee4f2e11bbcf565c33e6d83204aa6e9389158d34ca13</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Shimian</creatorcontrib><creatorcontrib>Bharadwaj, Skanda</creatorcontrib><creatorcontrib>Kraiger, Keaton</creatorcontrib><creatorcontrib>Asthana, Yashasvi</creatorcontrib><creatorcontrib>Zhang, Hong</creatorcontrib><creatorcontrib>Collins, Robert</creatorcontrib><creatorcontrib>Liu, Yanxi</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Zhang, Shimian</au><au>Bharadwaj, Skanda</au><au>Kraiger, Keaton</au><au>Asthana, Yashasvi</au><au>Zhang, Hong</au><au>Collins, Robert</au><au>Liu, Yanxi</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Novel 3D Scene Understanding Applications From Recurrence in a Single Image</atitle><date>2022-10-14</date><risdate>2022</risdate><abstract>We demonstrate the utility of recurring pattern discovery from a single image for spatial understanding of a 3D scene in terms of (1) vanishing point detection, (2) hypothesizing 3D translation symmetry and (3) counting the number of RP instances in the image. Furthermore, we illustrate the feasibility of leveraging RP discovery output to form a more precise, quantitative text description of the scene. Our quantitative evaluations on a new 1K+ Recurring Pattern (RP) benchmark with diverse variations show that visual perception of recurrence from one single view leads to scene understanding outcomes that are as good as or better than existing supervised methods and/or unsupervised methods that use millions of images.</abstract><doi>10.48550/arxiv.2210.07991</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2210.07991
ispartof
issn
language eng
recordid cdi_arxiv_primary_2210_07991
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
title Novel 3D Scene Understanding Applications From Recurrence in a Single Image
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-31T11%3A29%3A01IST&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=Novel%203D%20Scene%20Understanding%20Applications%20From%20Recurrence%20in%20a%20Single%20Image&rft.au=Zhang,%20Shimian&rft.date=2022-10-14&rft_id=info:doi/10.48550/arxiv.2210.07991&rft_dat=%3Carxiv_GOX%3E2210_07991%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