High resolution matting via interactive trimap segmentation
We present a new approach to the matting problem which splits the task into two steps: interactive trimap extraction followed by trimap-based alpha matting. By doing so we gain considerably in terms of speed and quality and are able to deal with high resolution images. This paper has three contribut...
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 8 |
|---|---|
| container_issue | |
| container_start_page | 1 |
| container_title | |
| container_volume | |
| creator | Rhemann, C. Rother, C. Rav-Acha, A. Sharp, T. |
| description | We present a new approach to the matting problem which splits the task into two steps: interactive trimap extraction followed by trimap-based alpha matting. By doing so we gain considerably in terms of speed and quality and are able to deal with high resolution images. This paper has three contributions: (i) a new trimap segmentation method using parametric max-flow; (ii) an alpha matting technique for high resolution images with a new gradient preserving prior on alpha; (iii) a database of 27 ground truth alpha mattes of still objects, which is considerably larger than previous databases and also of higher quality. The database is used to train our system and to validate that both our trimap extraction and our matting method improve on state-of-the-art techniques. |
| doi_str_mv | 10.1109/CVPR.2008.4587441 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_4587441</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4587441</ieee_id><sourcerecordid>4587441</sourcerecordid><originalsourceid>FETCH-LOGICAL-c138t-8f38bcc3ce483c1f4639ec453d838f1d6823b2ef3d596f587f15876d83887bea3</originalsourceid><addsrcrecordid>eNpVj0FLxDAQhSMquKz9AeKlf6A1k0nTBE9S1BUWFFGvS5pOamTbXdq44L-3xb34DvN4zDC8j7Er4DkANzfVx8trLjjXuSx0KSWcsMSUGqSQUgiJ4vRfFsUZWwBXmCkD5oIl4_jFJ8kCFagFu12F9jMdaNxtv2PY9WlnYwx9mx6CTUMfabAuhgOlcQid3acjtR310c63l-zc2-1IydGX7P3h_q1aZevnx6fqbp05QB0z7VHXzqEjqdGBlwoNualAo1F7aJQWWAvy2BRG-QnKwzTUvNVlTRaX7PrvbyCizX4uMvxsjvj4C1TsS8o</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>High resolution matting via interactive trimap segmentation</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Rhemann, C. ; Rother, C. ; Rav-Acha, A. ; Sharp, T.</creator><creatorcontrib>Rhemann, C. ; Rother, C. ; Rav-Acha, A. ; Sharp, T.</creatorcontrib><description>We present a new approach to the matting problem which splits the task into two steps: interactive trimap extraction followed by trimap-based alpha matting. By doing so we gain considerably in terms of speed and quality and are able to deal with high resolution images. This paper has three contributions: (i) a new trimap segmentation method using parametric max-flow; (ii) an alpha matting technique for high resolution images with a new gradient preserving prior on alpha; (iii) a database of 27 ground truth alpha mattes of still objects, which is considerably larger than previous databases and also of higher quality. The database is used to train our system and to validate that both our trimap extraction and our matting method improve on state-of-the-art techniques.</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.2008.4587441</identifier><language>eng</language><publisher>IEEE</publisher><subject>Brushes ; Image databases ; Image resolution ; Image segmentation ; Interactive systems ; Paints ; Pixel ; Scholarships ; Topology ; User interfaces</subject><ispartof>2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008, p.1-8</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c138t-8f38bcc3ce483c1f4639ec453d838f1d6823b2ef3d596f587f15876d83887bea3</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4587441$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2057,27924,54919</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4587441$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Rhemann, C.</creatorcontrib><creatorcontrib>Rother, C.</creatorcontrib><creatorcontrib>Rav-Acha, A.</creatorcontrib><creatorcontrib>Sharp, T.</creatorcontrib><title>High resolution matting via interactive trimap segmentation</title><title>2008 IEEE Conference on Computer Vision and Pattern Recognition</title><addtitle>CVPR</addtitle><description>We present a new approach to the matting problem which splits the task into two steps: interactive trimap extraction followed by trimap-based alpha matting. By doing so we gain considerably in terms of speed and quality and are able to deal with high resolution images. This paper has three contributions: (i) a new trimap segmentation method using parametric max-flow; (ii) an alpha matting technique for high resolution images with a new gradient preserving prior on alpha; (iii) a database of 27 ground truth alpha mattes of still objects, which is considerably larger than previous databases and also of higher quality. The database is used to train our system and to validate that both our trimap extraction and our matting method improve on state-of-the-art techniques.</description><subject>Brushes</subject><subject>Image databases</subject><subject>Image resolution</subject><subject>Image segmentation</subject><subject>Interactive systems</subject><subject>Paints</subject><subject>Pixel</subject><subject>Scholarships</subject><subject>Topology</subject><subject>User interfaces</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><sourceid>RIE</sourceid><recordid>eNpVj0FLxDAQhSMquKz9AeKlf6A1k0nTBE9S1BUWFFGvS5pOamTbXdq44L-3xb34DvN4zDC8j7Er4DkANzfVx8trLjjXuSx0KSWcsMSUGqSQUgiJ4vRfFsUZWwBXmCkD5oIl4_jFJ8kCFagFu12F9jMdaNxtv2PY9WlnYwx9mx6CTUMfabAuhgOlcQid3acjtR310c63l-zc2-1IydGX7P3h_q1aZevnx6fqbp05QB0z7VHXzqEjqdGBlwoNualAo1F7aJQWWAvy2BRG-QnKwzTUvNVlTRaX7PrvbyCizX4uMvxsjvj4C1TsS8o</recordid><startdate>200806</startdate><enddate>200806</enddate><creator>Rhemann, C.</creator><creator>Rother, C.</creator><creator>Rav-Acha, A.</creator><creator>Sharp, T.</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>High resolution matting via interactive trimap segmentation</title><author>Rhemann, C. ; Rother, C. ; Rav-Acha, A. ; Sharp, T.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c138t-8f38bcc3ce483c1f4639ec453d838f1d6823b2ef3d596f587f15876d83887bea3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Brushes</topic><topic>Image databases</topic><topic>Image resolution</topic><topic>Image segmentation</topic><topic>Interactive systems</topic><topic>Paints</topic><topic>Pixel</topic><topic>Scholarships</topic><topic>Topology</topic><topic>User interfaces</topic><toplevel>online_resources</toplevel><creatorcontrib>Rhemann, C.</creatorcontrib><creatorcontrib>Rother, C.</creatorcontrib><creatorcontrib>Rav-Acha, A.</creatorcontrib><creatorcontrib>Sharp, T.</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 Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Rhemann, C.</au><au>Rother, C.</au><au>Rav-Acha, A.</au><au>Sharp, T.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>High resolution matting via interactive trimap segmentation</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 present a new approach to the matting problem which splits the task into two steps: interactive trimap extraction followed by trimap-based alpha matting. By doing so we gain considerably in terms of speed and quality and are able to deal with high resolution images. This paper has three contributions: (i) a new trimap segmentation method using parametric max-flow; (ii) an alpha matting technique for high resolution images with a new gradient preserving prior on alpha; (iii) a database of 27 ground truth alpha mattes of still objects, which is considerably larger than previous databases and also of higher quality. The database is used to train our system and to validate that both our trimap extraction and our matting method improve on state-of-the-art techniques.</abstract><pub>IEEE</pub><doi>10.1109/CVPR.2008.4587441</doi><tpages>8</tpages></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_4587441 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Brushes Image databases Image resolution Image segmentation Interactive systems Paints Pixel Scholarships Topology User interfaces |
| title | High resolution matting via interactive trimap segmentation |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T14%3A02%3A47IST&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=High%20resolution%20matting%20via%20interactive%20trimap%20segmentation&rft.btitle=2008%20IEEE%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition&rft.au=Rhemann,%20C.&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.2008.4587441&rft_dat=%3Cieee_6IE%3E4587441%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781424422432&rft.eisbn_list=1424422434&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=4587441&rfr_iscdi=true |