ABO: Dataset and Benchmarks for Real-World 3D Object Understanding
We introduce Amazon Berkeley Objects (ABO), a new large-scale dataset designed to help bridge the gap between real and virtual 3D worlds. ABO contains product catalog images, metadata, and artist-created 3D models with complex geometries and physically-based materials that correspond to real, househ...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| 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 | Collins, Jasmine Goel, Shubham Deng, Kenan Luthra, Achleshwar Xu, Leon Gundogdu, Erhan Zhang, Xi Vicente, Tomas F. Yago Dideriksen, Thomas Arora, Himanshu Guillaumin, Matthieu Malik, Jitendra |
| description | We introduce Amazon Berkeley Objects (ABO), a new large-scale dataset
designed to help bridge the gap between real and virtual 3D worlds. ABO
contains product catalog images, metadata, and artist-created 3D models with
complex geometries and physically-based materials that correspond to real,
household objects. We derive challenging benchmarks that exploit the unique
properties of ABO and measure the current limits of the state-of-the-art on
three open problems for real-world 3D object understanding: single-view 3D
reconstruction, material estimation, and cross-domain multi-view object
retrieval. |
| doi_str_mv | 10.48550/arxiv.2110.06199 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2110_06199</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2110_06199</sourcerecordid><originalsourceid>FETCH-LOGICAL-a679-d7f7f1be9d6569d547c3eea3bd0ef65364a6ea01cd30cdd0269dbd9afdd046b13</originalsourceid><addsrcrecordid>eNotj0FPAjEUhHvhYJAf4Mn-gcWWbrvUGwuIJiSbGAzHzWvfqy4uC-lujPx7K3qayWQymY-xOymm-Vxr8QDxu_mazmQKhJHW3rByUVaPfAUD9DRw6JCX1PmPI8TPnodT5K8EbbY_xRa5WvHKHcgP_K1Div2Q6k33fstGAdqeJv86Zrun9W75nG2rzctysc3AFDbDIhRBOrJotLGo88IrIlAOBQWjlcnBEAjpUQmPKGap5NBCSD43Tqoxu_-bvULU59ikk5f6F6a-wqgf7hFEPg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>ABO: Dataset and Benchmarks for Real-World 3D Object Understanding</title><source>arXiv.org</source><creator>Collins, Jasmine ; Goel, Shubham ; Deng, Kenan ; Luthra, Achleshwar ; Xu, Leon ; Gundogdu, Erhan ; Zhang, Xi ; Vicente, Tomas F. Yago ; Dideriksen, Thomas ; Arora, Himanshu ; Guillaumin, Matthieu ; Malik, Jitendra</creator><creatorcontrib>Collins, Jasmine ; Goel, Shubham ; Deng, Kenan ; Luthra, Achleshwar ; Xu, Leon ; Gundogdu, Erhan ; Zhang, Xi ; Vicente, Tomas F. Yago ; Dideriksen, Thomas ; Arora, Himanshu ; Guillaumin, Matthieu ; Malik, Jitendra</creatorcontrib><description>We introduce Amazon Berkeley Objects (ABO), a new large-scale dataset
designed to help bridge the gap between real and virtual 3D worlds. ABO
contains product catalog images, metadata, and artist-created 3D models with
complex geometries and physically-based materials that correspond to real,
household objects. We derive challenging benchmarks that exploit the unique
properties of ABO and measure the current limits of the state-of-the-art on
three open problems for real-world 3D object understanding: single-view 3D
reconstruction, material estimation, and cross-domain multi-view object
retrieval.</description><identifier>DOI: 10.48550/arxiv.2110.06199</identifier><language>eng</language><subject>Computer Science - Artificial Intelligence ; Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Graphics</subject><creationdate>2021-10</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/2110.06199$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2110.06199$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Collins, Jasmine</creatorcontrib><creatorcontrib>Goel, Shubham</creatorcontrib><creatorcontrib>Deng, Kenan</creatorcontrib><creatorcontrib>Luthra, Achleshwar</creatorcontrib><creatorcontrib>Xu, Leon</creatorcontrib><creatorcontrib>Gundogdu, Erhan</creatorcontrib><creatorcontrib>Zhang, Xi</creatorcontrib><creatorcontrib>Vicente, Tomas F. Yago</creatorcontrib><creatorcontrib>Dideriksen, Thomas</creatorcontrib><creatorcontrib>Arora, Himanshu</creatorcontrib><creatorcontrib>Guillaumin, Matthieu</creatorcontrib><creatorcontrib>Malik, Jitendra</creatorcontrib><title>ABO: Dataset and Benchmarks for Real-World 3D Object Understanding</title><description>We introduce Amazon Berkeley Objects (ABO), a new large-scale dataset
designed to help bridge the gap between real and virtual 3D worlds. ABO
contains product catalog images, metadata, and artist-created 3D models with
complex geometries and physically-based materials that correspond to real,
household objects. We derive challenging benchmarks that exploit the unique
properties of ABO and measure the current limits of the state-of-the-art on
three open problems for real-world 3D object understanding: single-view 3D
reconstruction, material estimation, and cross-domain multi-view object
retrieval.</description><subject>Computer Science - Artificial Intelligence</subject><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Graphics</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj0FPAjEUhHvhYJAf4Mn-gcWWbrvUGwuIJiSbGAzHzWvfqy4uC-lujPx7K3qayWQymY-xOymm-Vxr8QDxu_mazmQKhJHW3rByUVaPfAUD9DRw6JCX1PmPI8TPnodT5K8EbbY_xRa5WvHKHcgP_K1Div2Q6k33fstGAdqeJv86Zrun9W75nG2rzctysc3AFDbDIhRBOrJotLGo88IrIlAOBQWjlcnBEAjpUQmPKGap5NBCSD43Tqoxu_-bvULU59ikk5f6F6a-wqgf7hFEPg</recordid><startdate>20211012</startdate><enddate>20211012</enddate><creator>Collins, Jasmine</creator><creator>Goel, Shubham</creator><creator>Deng, Kenan</creator><creator>Luthra, Achleshwar</creator><creator>Xu, Leon</creator><creator>Gundogdu, Erhan</creator><creator>Zhang, Xi</creator><creator>Vicente, Tomas F. Yago</creator><creator>Dideriksen, Thomas</creator><creator>Arora, Himanshu</creator><creator>Guillaumin, Matthieu</creator><creator>Malik, Jitendra</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20211012</creationdate><title>ABO: Dataset and Benchmarks for Real-World 3D Object Understanding</title><author>Collins, Jasmine ; Goel, Shubham ; Deng, Kenan ; Luthra, Achleshwar ; Xu, Leon ; Gundogdu, Erhan ; Zhang, Xi ; Vicente, Tomas F. Yago ; Dideriksen, Thomas ; Arora, Himanshu ; Guillaumin, Matthieu ; Malik, Jitendra</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a679-d7f7f1be9d6569d547c3eea3bd0ef65364a6ea01cd30cdd0269dbd9afdd046b13</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Computer Science - Artificial Intelligence</topic><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Graphics</topic><toplevel>online_resources</toplevel><creatorcontrib>Collins, Jasmine</creatorcontrib><creatorcontrib>Goel, Shubham</creatorcontrib><creatorcontrib>Deng, Kenan</creatorcontrib><creatorcontrib>Luthra, Achleshwar</creatorcontrib><creatorcontrib>Xu, Leon</creatorcontrib><creatorcontrib>Gundogdu, Erhan</creatorcontrib><creatorcontrib>Zhang, Xi</creatorcontrib><creatorcontrib>Vicente, Tomas F. Yago</creatorcontrib><creatorcontrib>Dideriksen, Thomas</creatorcontrib><creatorcontrib>Arora, Himanshu</creatorcontrib><creatorcontrib>Guillaumin, Matthieu</creatorcontrib><creatorcontrib>Malik, Jitendra</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Collins, Jasmine</au><au>Goel, Shubham</au><au>Deng, Kenan</au><au>Luthra, Achleshwar</au><au>Xu, Leon</au><au>Gundogdu, Erhan</au><au>Zhang, Xi</au><au>Vicente, Tomas F. Yago</au><au>Dideriksen, Thomas</au><au>Arora, Himanshu</au><au>Guillaumin, Matthieu</au><au>Malik, Jitendra</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>ABO: Dataset and Benchmarks for Real-World 3D Object Understanding</atitle><date>2021-10-12</date><risdate>2021</risdate><abstract>We introduce Amazon Berkeley Objects (ABO), a new large-scale dataset
designed to help bridge the gap between real and virtual 3D worlds. ABO
contains product catalog images, metadata, and artist-created 3D models with
complex geometries and physically-based materials that correspond to real,
household objects. We derive challenging benchmarks that exploit the unique
properties of ABO and measure the current limits of the state-of-the-art on
three open problems for real-world 3D object understanding: single-view 3D
reconstruction, material estimation, and cross-domain multi-view object
retrieval.</abstract><doi>10.48550/arxiv.2110.06199</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.2110.06199 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_2110_06199 |
| source | arXiv.org |
| subjects | Computer Science - Artificial Intelligence Computer Science - Computer Vision and Pattern Recognition Computer Science - Graphics |
| title | ABO: Dataset and Benchmarks for Real-World 3D Object Understanding |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T18%3A15%3A28IST&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=ABO:%20Dataset%20and%20Benchmarks%20for%20Real-World%203D%20Object%20Understanding&rft.au=Collins,%20Jasmine&rft.date=2021-10-12&rft_id=info:doi/10.48550/arxiv.2110.06199&rft_dat=%3Carxiv_GOX%3E2110_06199%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 |