Loading…
A fast local descriptor for dense matching
We introduce a novel local image descriptor designed for dense wide-baseline matching purposes. We feed our descriptors to a graph-cuts based dense depth map estimation algorithm and this yields better wide-baseline performance than the commonly used correlation windows for which the size is hard to...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Citations: | Items that cite this one |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | cdi_FETCH-LOGICAL-c1813-f8d45e427e032316277b36fa6912ecd9965617b6f5abb9ae4a9ab193fae0d0493 |
|---|---|
| cites | |
| container_end_page | 8 |
| container_issue | |
| container_start_page | 1 |
| container_title | |
| container_volume | |
| creator | Tola, E. Lepetit, V. Fua, P. |
| description | We introduce a novel local image descriptor designed for dense wide-baseline matching purposes. We feed our descriptors to a graph-cuts based dense depth map estimation algorithm and this yields better wide-baseline performance than the commonly used correlation windows for which the size is hard to tune. As a result, unlike competing techniques that require many high-resolution images to produce good reconstructions, our descriptor can compute them from pairs of low-quality images such as the ones captured by video streams. Our descriptor is inspired from earlier ones such as SIFT and GLOH but can be computed much faster for our purposes. Unlike SURF which can also be computed efficiently at every pixel, it does not introduce artifacts that degrade the matching performance. Our approach was tested with ground truth laser scanned depth maps as well as on a wide variety of image pairs of different resolutions and we show that good reconstructions are achieved even with only two low quality images. |
| doi_str_mv | 10.1109/CVPR.2008.4587673 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_4587673</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4587673</ieee_id><sourcerecordid>4587673</sourcerecordid><originalsourceid>FETCH-LOGICAL-c1813-f8d45e427e032316277b36fa6912ecd9965617b6f5abb9ae4a9ab193fae0d0493</originalsourceid><addsrcrecordid>eNpVj0tLxEAQhEdUcFnzA8TLnIXE6el5ZI5L8AULiqjXpZPp0Uj2QSYX_70B92JBUXyXKkqIK1AVgAq3zcfLa6WVqitja-88nogi-BqMNkZrg_r0H2t7JhagHJYuQLgQRc7fapax6MAtxM1KJsqTHPYdDTJy7sb-MO1HmWZH3mWWW5q6r373eSnOEw2Zi2Muxfv93VvzWK6fH56a1brsoAYsUx2NZaM9K9QITnvfoks072vuYgjOOvCtS5baNhAbCtRCwESsojIBl-L6r7dn5s1h7Lc0_myOb_EXxsZEJA</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A fast local descriptor for dense matching</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Tola, E. ; Lepetit, V. ; Fua, P.</creator><creatorcontrib>Tola, E. ; Lepetit, V. ; Fua, P.</creatorcontrib><description>We introduce a novel local image descriptor designed for dense wide-baseline matching purposes. We feed our descriptors to a graph-cuts based dense depth map estimation algorithm and this yields better wide-baseline performance than the commonly used correlation windows for which the size is hard to tune. As a result, unlike competing techniques that require many high-resolution images to produce good reconstructions, our descriptor can compute them from pairs of low-quality images such as the ones captured by video streams. Our descriptor is inspired from earlier ones such as SIFT and GLOH but can be computed much faster for our purposes. Unlike SURF which can also be computed efficiently at every pixel, it does not introduce artifacts that degrade the matching performance. Our approach was tested with ground truth laser scanned depth maps as well as on a wide variety of image pairs of different resolutions and we show that good reconstructions are achieved even with only two low quality images.</description><identifier>ISSN: 1063-6919</identifier><identifier>ISBN: 9781424422425</identifier><identifier>ISBN: 1424422426</identifier><identifier>EISBN: 9781424422432</identifier><identifier>EISBN: 1424422434</identifier><identifier>DOI: 10.1109/CVPR.2008.4587673</identifier><language>eng</language><publisher>IEEE</publisher><subject>Computational efficiency ; Computer vision ; Feeds ; Histograms ; Image reconstruction ; Laboratories ; Layout ; Pixel ; Robustness ; Yield estimation</subject><ispartof>2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008, p.1-8</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c1813-f8d45e427e032316277b36fa6912ecd9965617b6f5abb9ae4a9ab193fae0d0493</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4587673$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2057,27924,54919</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4587673$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Tola, E.</creatorcontrib><creatorcontrib>Lepetit, V.</creatorcontrib><creatorcontrib>Fua, P.</creatorcontrib><title>A fast local descriptor for dense matching</title><title>2008 IEEE Conference on Computer Vision and Pattern Recognition</title><addtitle>CVPR</addtitle><description>We introduce a novel local image descriptor designed for dense wide-baseline matching purposes. We feed our descriptors to a graph-cuts based dense depth map estimation algorithm and this yields better wide-baseline performance than the commonly used correlation windows for which the size is hard to tune. As a result, unlike competing techniques that require many high-resolution images to produce good reconstructions, our descriptor can compute them from pairs of low-quality images such as the ones captured by video streams. Our descriptor is inspired from earlier ones such as SIFT and GLOH but can be computed much faster for our purposes. Unlike SURF which can also be computed efficiently at every pixel, it does not introduce artifacts that degrade the matching performance. Our approach was tested with ground truth laser scanned depth maps as well as on a wide variety of image pairs of different resolutions and we show that good reconstructions are achieved even with only two low quality images.</description><subject>Computational efficiency</subject><subject>Computer vision</subject><subject>Feeds</subject><subject>Histograms</subject><subject>Image reconstruction</subject><subject>Laboratories</subject><subject>Layout</subject><subject>Pixel</subject><subject>Robustness</subject><subject>Yield estimation</subject><issn>1063-6919</issn><isbn>9781424422425</isbn><isbn>1424422426</isbn><isbn>9781424422432</isbn><isbn>1424422434</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2008</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNpVj0tLxEAQhEdUcFnzA8TLnIXE6el5ZI5L8AULiqjXpZPp0Uj2QSYX_70B92JBUXyXKkqIK1AVgAq3zcfLa6WVqitja-88nogi-BqMNkZrg_r0H2t7JhagHJYuQLgQRc7fapax6MAtxM1KJsqTHPYdDTJy7sb-MO1HmWZH3mWWW5q6r373eSnOEw2Zi2Muxfv93VvzWK6fH56a1brsoAYsUx2NZaM9K9QITnvfoks072vuYgjOOvCtS5baNhAbCtRCwESsojIBl-L6r7dn5s1h7Lc0_myOb_EXxsZEJA</recordid><startdate>200806</startdate><enddate>200806</enddate><creator>Tola, E.</creator><creator>Lepetit, V.</creator><creator>Fua, P.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>200806</creationdate><title>A fast local descriptor for dense matching</title><author>Tola, E. ; Lepetit, V. ; Fua, P.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c1813-f8d45e427e032316277b36fa6912ecd9965617b6f5abb9ae4a9ab193fae0d0493</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Computational efficiency</topic><topic>Computer vision</topic><topic>Feeds</topic><topic>Histograms</topic><topic>Image reconstruction</topic><topic>Laboratories</topic><topic>Layout</topic><topic>Pixel</topic><topic>Robustness</topic><topic>Yield estimation</topic><toplevel>online_resources</toplevel><creatorcontrib>Tola, E.</creatorcontrib><creatorcontrib>Lepetit, V.</creatorcontrib><creatorcontrib>Fua, P.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Xplore</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Tola, E.</au><au>Lepetit, V.</au><au>Fua, P.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A fast local descriptor for dense matching</atitle><btitle>2008 IEEE Conference on Computer Vision and Pattern Recognition</btitle><stitle>CVPR</stitle><date>2008-06</date><risdate>2008</risdate><spage>1</spage><epage>8</epage><pages>1-8</pages><issn>1063-6919</issn><isbn>9781424422425</isbn><isbn>1424422426</isbn><eisbn>9781424422432</eisbn><eisbn>1424422434</eisbn><abstract>We introduce a novel local image descriptor designed for dense wide-baseline matching purposes. We feed our descriptors to a graph-cuts based dense depth map estimation algorithm and this yields better wide-baseline performance than the commonly used correlation windows for which the size is hard to tune. As a result, unlike competing techniques that require many high-resolution images to produce good reconstructions, our descriptor can compute them from pairs of low-quality images such as the ones captured by video streams. Our descriptor is inspired from earlier ones such as SIFT and GLOH but can be computed much faster for our purposes. Unlike SURF which can also be computed efficiently at every pixel, it does not introduce artifacts that degrade the matching performance. Our approach was tested with ground truth laser scanned depth maps as well as on a wide variety of image pairs of different resolutions and we show that good reconstructions are achieved even with only two low quality images.</abstract><pub>IEEE</pub><doi>10.1109/CVPR.2008.4587673</doi><tpages>8</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1063-6919 |
| ispartof | 2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008, p.1-8 |
| issn | 1063-6919 |
| language | eng |
| recordid | cdi_ieee_primary_4587673 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Computational efficiency Computer vision Feeds Histograms Image reconstruction Laboratories Layout Pixel Robustness Yield estimation |
| title | A fast local descriptor for dense matching |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T11%3A03%3A51IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=A%20fast%20local%20descriptor%20for%20dense%20matching&rft.btitle=2008%20IEEE%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition&rft.au=Tola,%20E.&rft.date=2008-06&rft.spage=1&rft.epage=8&rft.pages=1-8&rft.issn=1063-6919&rft.isbn=9781424422425&rft.isbn_list=1424422426&rft_id=info:doi/10.1109/CVPR.2008.4587673&rft.eisbn=9781424422432&rft.eisbn_list=1424422434&rft_dat=%3Cieee_6IE%3E4587673%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c1813-f8d45e427e032316277b36fa6912ecd9965617b6f5abb9ae4a9ab193fae0d0493%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=4587673&rfr_iscdi=true |