Video object inpainting using posture mapping
This paper presents a novel framework for object-based video inpainting. To complete an occluded object, our method first samples a 3-D volume of the video into directional spatio-temporal slices, and then performs patch-based image inpainting to repair the partially damaged object trajectories in t...
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 | 2788 |
|---|---|
| container_issue | |
| container_start_page | 2785 |
| container_title | |
| container_volume | |
| creator | Chih-Hung Ling Chia-Wen Lin Chih-Wen Su Liao, H.-Y.M. Yong-Sheng Chen |
| description | This paper presents a novel framework for object-based video inpainting. To complete an occluded object, our method first samples a 3-D volume of the video into directional spatio-temporal slices, and then performs patch-based image inpainting to repair the partially damaged object trajectories in the 2-D slices. The completed slices are subsequently combined to obtain a sequence of virtual contours of the damaged object. The virtual contours and a posture sequence retrieval technique are then used to retrieve the most similar sequence of object postures in the available non-occluded postures. Key-posture selection and indexing are performed to reduce the complexity of posture sequence retrieval. We also propose a synthetic posture generation scheme that enriches the collection of key-postures so as to reduce the effect of insufficient key-postures. Our experimental results demonstrate that the proposed method can maintain the spatial consistency and temporal motion continuity of an object simultaneously. |
| doi_str_mv | 10.1109/ICIP.2009.5414183 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_5414183</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5414183</ieee_id><sourcerecordid>5414183</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-837bd16e90183e619a7e8050ecf4cf14035c0a56bf9580a15a2646a19cd9c7953</originalsourceid><addsrcrecordid>eNpVj81OwzAQhM2fRCh9AMQlL-Cwa3sd-4gifiJVggNwrRxng1zRJGrSA29PEb1wmdHok0YzQtwgFIjg7-qqfi0UgC_IoEGnT8TSlw6NMoYsEZyKTGmH0pHxZ_-YtuciQ1JKGufgUlxN0wZAAWrMhPxILQ_50Gw4znnqx5D6OfWf-X761XGY5v2O820Yx0O-Fhdd-Jp4efSFeH98eKue5erlqa7uVzJhSbN0umxatOzhMJQt-lCyAwKOnYkdGtAUIZBtOk8OAlJQ1tiAPrY-lp70Qtz-9SZmXo-7tA277_Xxuf4BgydGvQ</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Video object inpainting using posture mapping</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Chih-Hung Ling ; Chia-Wen Lin ; Chih-Wen Su ; Liao, H.-Y.M. ; Yong-Sheng Chen</creator><creatorcontrib>Chih-Hung Ling ; Chia-Wen Lin ; Chih-Wen Su ; Liao, H.-Y.M. ; Yong-Sheng Chen</creatorcontrib><description>This paper presents a novel framework for object-based video inpainting. To complete an occluded object, our method first samples a 3-D volume of the video into directional spatio-temporal slices, and then performs patch-based image inpainting to repair the partially damaged object trajectories in the 2-D slices. The completed slices are subsequently combined to obtain a sequence of virtual contours of the damaged object. The virtual contours and a posture sequence retrieval technique are then used to retrieve the most similar sequence of object postures in the available non-occluded postures. Key-posture selection and indexing are performed to reduce the complexity of posture sequence retrieval. We also propose a synthetic posture generation scheme that enriches the collection of key-postures so as to reduce the effect of insufficient key-postures. Our experimental results demonstrate that the proposed method can maintain the spatial consistency and temporal motion continuity of an object simultaneously.</description><identifier>ISSN: 1522-4880</identifier><identifier>ISBN: 9781424456536</identifier><identifier>ISBN: 1424456533</identifier><identifier>EISSN: 2381-8549</identifier><identifier>EISBN: 9781424456550</identifier><identifier>EISBN: 9781424456543</identifier><identifier>EISBN: 142445655X</identifier><identifier>EISBN: 1424456541</identifier><identifier>DOI: 10.1109/ICIP.2009.5414183</identifier><language>eng</language><publisher>IEEE</publisher><subject>Cameras ; Computer science ; Filling ; Image reconstruction ; Information science ; Lighting ; object completion ; posture mapping ; synthetic posture ; Tensile stress ; video inpainitng ; Visual effects ; Voting</subject><ispartof>2009 16th IEEE International Conference on Image Processing (ICIP), 2009, p.2785-2788</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/5414183$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,27904,54898</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5414183$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Chih-Hung Ling</creatorcontrib><creatorcontrib>Chia-Wen Lin</creatorcontrib><creatorcontrib>Chih-Wen Su</creatorcontrib><creatorcontrib>Liao, H.-Y.M.</creatorcontrib><creatorcontrib>Yong-Sheng Chen</creatorcontrib><title>Video object inpainting using posture mapping</title><title>2009 16th IEEE International Conference on Image Processing (ICIP)</title><addtitle>ICIP</addtitle><description>This paper presents a novel framework for object-based video inpainting. To complete an occluded object, our method first samples a 3-D volume of the video into directional spatio-temporal slices, and then performs patch-based image inpainting to repair the partially damaged object trajectories in the 2-D slices. The completed slices are subsequently combined to obtain a sequence of virtual contours of the damaged object. The virtual contours and a posture sequence retrieval technique are then used to retrieve the most similar sequence of object postures in the available non-occluded postures. Key-posture selection and indexing are performed to reduce the complexity of posture sequence retrieval. We also propose a synthetic posture generation scheme that enriches the collection of key-postures so as to reduce the effect of insufficient key-postures. Our experimental results demonstrate that the proposed method can maintain the spatial consistency and temporal motion continuity of an object simultaneously.</description><subject>Cameras</subject><subject>Computer science</subject><subject>Filling</subject><subject>Image reconstruction</subject><subject>Information science</subject><subject>Lighting</subject><subject>object completion</subject><subject>posture mapping</subject><subject>synthetic posture</subject><subject>Tensile stress</subject><subject>video inpainitng</subject><subject>Visual effects</subject><subject>Voting</subject><issn>1522-4880</issn><issn>2381-8549</issn><isbn>9781424456536</isbn><isbn>1424456533</isbn><isbn>9781424456550</isbn><isbn>9781424456543</isbn><isbn>142445655X</isbn><isbn>1424456541</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2009</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNpVj81OwzAQhM2fRCh9AMQlL-Cwa3sd-4gifiJVggNwrRxng1zRJGrSA29PEb1wmdHok0YzQtwgFIjg7-qqfi0UgC_IoEGnT8TSlw6NMoYsEZyKTGmH0pHxZ_-YtuciQ1JKGufgUlxN0wZAAWrMhPxILQ_50Gw4znnqx5D6OfWf-X761XGY5v2O820Yx0O-Fhdd-Jp4efSFeH98eKue5erlqa7uVzJhSbN0umxatOzhMJQt-lCyAwKOnYkdGtAUIZBtOk8OAlJQ1tiAPrY-lp70Qtz-9SZmXo-7tA277_Xxuf4BgydGvQ</recordid><startdate>200911</startdate><enddate>200911</enddate><creator>Chih-Hung Ling</creator><creator>Chia-Wen Lin</creator><creator>Chih-Wen Su</creator><creator>Liao, H.-Y.M.</creator><creator>Yong-Sheng Chen</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>200911</creationdate><title>Video object inpainting using posture mapping</title><author>Chih-Hung Ling ; Chia-Wen Lin ; Chih-Wen Su ; Liao, H.-Y.M. ; Yong-Sheng Chen</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-837bd16e90183e619a7e8050ecf4cf14035c0a56bf9580a15a2646a19cd9c7953</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2009</creationdate><topic>Cameras</topic><topic>Computer science</topic><topic>Filling</topic><topic>Image reconstruction</topic><topic>Information science</topic><topic>Lighting</topic><topic>object completion</topic><topic>posture mapping</topic><topic>synthetic posture</topic><topic>Tensile stress</topic><topic>video inpainitng</topic><topic>Visual effects</topic><topic>Voting</topic><toplevel>online_resources</toplevel><creatorcontrib>Chih-Hung Ling</creatorcontrib><creatorcontrib>Chia-Wen Lin</creatorcontrib><creatorcontrib>Chih-Wen Su</creatorcontrib><creatorcontrib>Liao, H.-Y.M.</creatorcontrib><creatorcontrib>Yong-Sheng Chen</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 Online</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Chih-Hung Ling</au><au>Chia-Wen Lin</au><au>Chih-Wen Su</au><au>Liao, H.-Y.M.</au><au>Yong-Sheng Chen</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Video object inpainting using posture mapping</atitle><btitle>2009 16th IEEE International Conference on Image Processing (ICIP)</btitle><stitle>ICIP</stitle><date>2009-11</date><risdate>2009</risdate><spage>2785</spage><epage>2788</epage><pages>2785-2788</pages><issn>1522-4880</issn><eissn>2381-8549</eissn><isbn>9781424456536</isbn><isbn>1424456533</isbn><eisbn>9781424456550</eisbn><eisbn>9781424456543</eisbn><eisbn>142445655X</eisbn><eisbn>1424456541</eisbn><abstract>This paper presents a novel framework for object-based video inpainting. To complete an occluded object, our method first samples a 3-D volume of the video into directional spatio-temporal slices, and then performs patch-based image inpainting to repair the partially damaged object trajectories in the 2-D slices. The completed slices are subsequently combined to obtain a sequence of virtual contours of the damaged object. The virtual contours and a posture sequence retrieval technique are then used to retrieve the most similar sequence of object postures in the available non-occluded postures. Key-posture selection and indexing are performed to reduce the complexity of posture sequence retrieval. We also propose a synthetic posture generation scheme that enriches the collection of key-postures so as to reduce the effect of insufficient key-postures. Our experimental results demonstrate that the proposed method can maintain the spatial consistency and temporal motion continuity of an object simultaneously.</abstract><pub>IEEE</pub><doi>10.1109/ICIP.2009.5414183</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1522-4880 |
| ispartof | 2009 16th IEEE International Conference on Image Processing (ICIP), 2009, p.2785-2788 |
| issn | 1522-4880 2381-8549 |
| language | eng |
| recordid | cdi_ieee_primary_5414183 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Cameras Computer science Filling Image reconstruction Information science Lighting object completion posture mapping synthetic posture Tensile stress video inpainitng Visual effects Voting |
| title | Video object inpainting using posture mapping |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-27T21%3A39%3A04IST&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=Video%20object%20inpainting%20using%20posture%20mapping&rft.btitle=2009%2016th%20IEEE%20International%20Conference%20on%20Image%20Processing%20(ICIP)&rft.au=Chih-Hung%20Ling&rft.date=2009-11&rft.spage=2785&rft.epage=2788&rft.pages=2785-2788&rft.issn=1522-4880&rft.eissn=2381-8549&rft.isbn=9781424456536&rft.isbn_list=1424456533&rft_id=info:doi/10.1109/ICIP.2009.5414183&rft_dat=%3Cieee_6IE%3E5414183%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781424456550&rft.eisbn_list=9781424456543&rft.eisbn_list=142445655X&rft.eisbn_list=1424456541&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5414183&rfr_iscdi=true |