Calipso: physics-based image and video editing through CAD model proxies

We present Calipso, an interactive method for editing images and videos in a physically coherent manner. Our main idea is to realize physics-based manipulations by running a full-physics simulation on proxy geometries given by non-rigidly aligned CAD models. Running these simulations allows us to ap...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:The Visual computer 2020-01, Vol.36 (1), p.211-226
Hauptverfasser: Haouchine, Nazim, Roy, Frederick, Courtecuisse, Hadrien, Nießner, Matthias, Cotin, Stephane
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 226
container_issue 1
container_start_page 211
container_title The Visual computer
container_volume 36
creator Haouchine, Nazim
Roy, Frederick
Courtecuisse, Hadrien
Nießner, Matthias
Cotin, Stephane
description We present Calipso, an interactive method for editing images and videos in a physically coherent manner. Our main idea is to realize physics-based manipulations by running a full-physics simulation on proxy geometries given by non-rigidly aligned CAD models. Running these simulations allows us to apply new, unseen forces to move or deform selected objects, change physical parameters such as mass or elasticity, or even add entire new objects that interact with the rest of the underlying scene. In our method, the user makes edits directly in 3D; these edits are processed by the simulation and then transferred to the target 2D content using shape-to-image correspondences in a photo-realistic rendering process. To align the CAD models, we introduce an efficient CAD-to-image alignment procedure that jointly minimizes for rigid and non-rigid alignment while preserving the high-level structure of the input shape. Moreover, the user can choose to exploit image flow to estimate scene motion, producing coherent physical behavior with ambient dynamics. We demonstrate physics-based editing on a wide range of examples producing myriad physical behavior while preserving geometric and visual consistency.
doi_str_mv 10.1007/s00371-018-1600-0
format Article
fullrecord <record><control><sourceid>proquest_webof</sourceid><recordid>TN_cdi_webofscience_primary_000511966800016</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2917937777</sourcerecordid><originalsourceid>FETCH-LOGICAL-c393t-c4c385827f8268b8d4059f7b980c4f54ea98f40733f09bfba6824ae2bea6cbad3</originalsourceid><addsrcrecordid>eNqNkM1qGzEUhUVooG6SB-hOkFUpSq9-ZiR1Z6ZJXTBkk6yFRiPZMvbIHY2d5O0rM8VZFarNlS7fORwdhD5TuKMA8lsG4JISoIrQGoDABZpRwRlhnFYf0AyoVIRJpT-iTzlvoLyl0DO0aOw27nP6jvfrtxxdJq3NvsNxZ1ce277Dx9j5hH0Xx9iv8Lge0mG1xs38B96lzm_xfkiv0edrdBnsNvubv_MKPT_cPzULsnz8-auZL4njmo_ECcdVpZgMitWqVZ2ASgfZagVOhEp4q1UQIDkPoNvQ2loxYT1rva1dazt-hb5Mvmu7Nfuh5BzeTLLRLOZLc9qVCjTUShxZYW8ntmT8ffB5NJt0GPoSzzBNpeaynELRiXJDynnw4WxLwZzKNVO5J2dzKtdA0XydNC--TSG76HvnzzoAqCjVda3KjdaFVv9PN3G0Y0x9kw79WKRskuaC9ys_vH_h3-n-AM0mm18</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2917937777</pqid></control><display><type>article</type><title>Calipso: physics-based image and video editing through CAD model proxies</title><source>SpringerNature Journals</source><source>Web of Science - Science Citation Index Expanded - 2020&lt;img src="https://exlibris-pub.s3.amazonaws.com/fromwos-v2.jpg" /&gt;</source><source>Proquest Central</source><source>ProQuest Central UK/Ireland</source><creator>Haouchine, Nazim ; Roy, Frederick ; Courtecuisse, Hadrien ; Nießner, Matthias ; Cotin, Stephane</creator><creatorcontrib>Haouchine, Nazim ; Roy, Frederick ; Courtecuisse, Hadrien ; Nießner, Matthias ; Cotin, Stephane</creatorcontrib><description>We present Calipso, an interactive method for editing images and videos in a physically coherent manner. Our main idea is to realize physics-based manipulations by running a full-physics simulation on proxy geometries given by non-rigidly aligned CAD models. Running these simulations allows us to apply new, unseen forces to move or deform selected objects, change physical parameters such as mass or elasticity, or even add entire new objects that interact with the rest of the underlying scene. In our method, the user makes edits directly in 3D; these edits are processed by the simulation and then transferred to the target 2D content using shape-to-image correspondences in a photo-realistic rendering process. To align the CAD models, we introduce an efficient CAD-to-image alignment procedure that jointly minimizes for rigid and non-rigid alignment while preserving the high-level structure of the input shape. Moreover, the user can choose to exploit image flow to estimate scene motion, producing coherent physical behavior with ambient dynamics. We demonstrate physics-based editing on a wide range of examples producing myriad physical behavior while preserving geometric and visual consistency.</description><identifier>ISSN: 0178-2789</identifier><identifier>EISSN: 1432-2315</identifier><identifier>EISSN: 1432-8726</identifier><identifier>DOI: 10.1007/s00371-018-1600-0</identifier><language>eng</language><publisher>Berlin/Heidelberg: Springer Berlin Heidelberg</publisher><subject>Alignment ; Artificial Intelligence ; Computer Graphics ; Computer Science ; Computer Science, Software Engineering ; Editing ; Geometry ; Graphics ; Human-Computer Interaction ; Image Processing and Computer Vision ; Original Article ; Physical properties ; Physics ; Science &amp; Technology ; Simulation ; Technology</subject><ispartof>The Visual computer, 2020-01, Vol.36 (1), p.211-226</ispartof><rights>Springer-Verlag GmbH Germany, part of Springer Nature 2018</rights><rights>Springer-Verlag GmbH Germany, part of Springer Nature 2018.</rights><rights>Distributed under a Creative Commons Attribution 4.0 International License</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>true</woscitedreferencessubscribed><woscitedreferencescount>5</woscitedreferencescount><woscitedreferencesoriginalsourcerecordid>wos000511966800016</woscitedreferencesoriginalsourcerecordid><citedby>FETCH-LOGICAL-c393t-c4c385827f8268b8d4059f7b980c4f54ea98f40733f09bfba6824ae2bea6cbad3</citedby><cites>FETCH-LOGICAL-c393t-c4c385827f8268b8d4059f7b980c4f54ea98f40733f09bfba6824ae2bea6cbad3</cites><orcidid>0000-0002-1752-3479 ; 0000-0001-6342-2284 ; 0000-0002-2661-505X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s00371-018-1600-0$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://www.proquest.com/docview/2917937777?pq-origsite=primo$$EHTML$$P50$$Gproquest$$H</linktohtml><link.rule.ids>230,315,782,786,887,21395,27931,27932,28255,33751,41495,42564,43812,51326,64392,64396,72476</link.rule.ids><backlink>$$Uhttps://inria.hal.science/hal-01890684$$DView record in HAL$$Hfree_for_read</backlink></links><search><creatorcontrib>Haouchine, Nazim</creatorcontrib><creatorcontrib>Roy, Frederick</creatorcontrib><creatorcontrib>Courtecuisse, Hadrien</creatorcontrib><creatorcontrib>Nießner, Matthias</creatorcontrib><creatorcontrib>Cotin, Stephane</creatorcontrib><title>Calipso: physics-based image and video editing through CAD model proxies</title><title>The Visual computer</title><addtitle>Vis Comput</addtitle><addtitle>VISUAL COMPUT</addtitle><description>We present Calipso, an interactive method for editing images and videos in a physically coherent manner. Our main idea is to realize physics-based manipulations by running a full-physics simulation on proxy geometries given by non-rigidly aligned CAD models. Running these simulations allows us to apply new, unseen forces to move or deform selected objects, change physical parameters such as mass or elasticity, or even add entire new objects that interact with the rest of the underlying scene. In our method, the user makes edits directly in 3D; these edits are processed by the simulation and then transferred to the target 2D content using shape-to-image correspondences in a photo-realistic rendering process. To align the CAD models, we introduce an efficient CAD-to-image alignment procedure that jointly minimizes for rigid and non-rigid alignment while preserving the high-level structure of the input shape. Moreover, the user can choose to exploit image flow to estimate scene motion, producing coherent physical behavior with ambient dynamics. We demonstrate physics-based editing on a wide range of examples producing myriad physical behavior while preserving geometric and visual consistency.</description><subject>Alignment</subject><subject>Artificial Intelligence</subject><subject>Computer Graphics</subject><subject>Computer Science</subject><subject>Computer Science, Software Engineering</subject><subject>Editing</subject><subject>Geometry</subject><subject>Graphics</subject><subject>Human-Computer Interaction</subject><subject>Image Processing and Computer Vision</subject><subject>Original Article</subject><subject>Physical properties</subject><subject>Physics</subject><subject>Science &amp; Technology</subject><subject>Simulation</subject><subject>Technology</subject><issn>0178-2789</issn><issn>1432-2315</issn><issn>1432-8726</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>AOWDO</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><recordid>eNqNkM1qGzEUhUVooG6SB-hOkFUpSq9-ZiR1Z6ZJXTBkk6yFRiPZMvbIHY2d5O0rM8VZFarNlS7fORwdhD5TuKMA8lsG4JISoIrQGoDABZpRwRlhnFYf0AyoVIRJpT-iTzlvoLyl0DO0aOw27nP6jvfrtxxdJq3NvsNxZ1ce277Dx9j5hH0Xx9iv8Lge0mG1xs38B96lzm_xfkiv0edrdBnsNvubv_MKPT_cPzULsnz8-auZL4njmo_ECcdVpZgMitWqVZ2ASgfZagVOhEp4q1UQIDkPoNvQ2loxYT1rva1dazt-hb5Mvmu7Nfuh5BzeTLLRLOZLc9qVCjTUShxZYW8ntmT8ffB5NJt0GPoSzzBNpeaynELRiXJDynnw4WxLwZzKNVO5J2dzKtdA0XydNC--TSG76HvnzzoAqCjVda3KjdaFVv9PN3G0Y0x9kw79WKRskuaC9ys_vH_h3-n-AM0mm18</recordid><startdate>20200101</startdate><enddate>20200101</enddate><creator>Haouchine, Nazim</creator><creator>Roy, Frederick</creator><creator>Courtecuisse, Hadrien</creator><creator>Nießner, Matthias</creator><creator>Cotin, Stephane</creator><general>Springer Berlin Heidelberg</general><general>Springer Nature</general><general>Springer Nature B.V</general><general>Springer Verlag</general><scope>AOWDO</scope><scope>BLEPL</scope><scope>DTL</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>8FE</scope><scope>8FG</scope><scope>AFKRA</scope><scope>ARAPS</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>HCIFZ</scope><scope>JQ2</scope><scope>K7-</scope><scope>P5Z</scope><scope>P62</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>1XC</scope><scope>VOOES</scope><orcidid>https://orcid.org/0000-0002-1752-3479</orcidid><orcidid>https://orcid.org/0000-0001-6342-2284</orcidid><orcidid>https://orcid.org/0000-0002-2661-505X</orcidid></search><sort><creationdate>20200101</creationdate><title>Calipso: physics-based image and video editing through CAD model proxies</title><author>Haouchine, Nazim ; Roy, Frederick ; Courtecuisse, Hadrien ; Nießner, Matthias ; Cotin, Stephane</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c393t-c4c385827f8268b8d4059f7b980c4f54ea98f40733f09bfba6824ae2bea6cbad3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Alignment</topic><topic>Artificial Intelligence</topic><topic>Computer Graphics</topic><topic>Computer Science</topic><topic>Computer Science, Software Engineering</topic><topic>Editing</topic><topic>Geometry</topic><topic>Graphics</topic><topic>Human-Computer Interaction</topic><topic>Image Processing and Computer Vision</topic><topic>Original Article</topic><topic>Physical properties</topic><topic>Physics</topic><topic>Science &amp; Technology</topic><topic>Simulation</topic><topic>Technology</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Haouchine, Nazim</creatorcontrib><creatorcontrib>Roy, Frederick</creatorcontrib><creatorcontrib>Courtecuisse, Hadrien</creatorcontrib><creatorcontrib>Nießner, Matthias</creatorcontrib><creatorcontrib>Cotin, Stephane</creatorcontrib><collection>Web of Science - Science Citation Index Expanded - 2020</collection><collection>Web of Science Core Collection</collection><collection>Science Citation Index Expanded</collection><collection>CrossRef</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>ProQuest Central UK/Ireland</collection><collection>Advanced Technologies &amp; Aerospace Collection</collection><collection>ProQuest Central Essentials</collection><collection>Proquest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>ProQuest Central Student</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Computer Science Collection</collection><collection>Computer Science Database</collection><collection>Advanced Technologies &amp; Aerospace Database</collection><collection>ProQuest Advanced Technologies &amp; Aerospace Collection</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>Hyper Article en Ligne (HAL)</collection><collection>Hyper Article en Ligne (HAL) (Open Access)</collection><jtitle>The Visual computer</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Haouchine, Nazim</au><au>Roy, Frederick</au><au>Courtecuisse, Hadrien</au><au>Nießner, Matthias</au><au>Cotin, Stephane</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Calipso: physics-based image and video editing through CAD model proxies</atitle><jtitle>The Visual computer</jtitle><stitle>Vis Comput</stitle><stitle>VISUAL COMPUT</stitle><date>2020-01-01</date><risdate>2020</risdate><volume>36</volume><issue>1</issue><spage>211</spage><epage>226</epage><pages>211-226</pages><issn>0178-2789</issn><eissn>1432-2315</eissn><eissn>1432-8726</eissn><abstract>We present Calipso, an interactive method for editing images and videos in a physically coherent manner. Our main idea is to realize physics-based manipulations by running a full-physics simulation on proxy geometries given by non-rigidly aligned CAD models. Running these simulations allows us to apply new, unseen forces to move or deform selected objects, change physical parameters such as mass or elasticity, or even add entire new objects that interact with the rest of the underlying scene. In our method, the user makes edits directly in 3D; these edits are processed by the simulation and then transferred to the target 2D content using shape-to-image correspondences in a photo-realistic rendering process. To align the CAD models, we introduce an efficient CAD-to-image alignment procedure that jointly minimizes for rigid and non-rigid alignment while preserving the high-level structure of the input shape. Moreover, the user can choose to exploit image flow to estimate scene motion, producing coherent physical behavior with ambient dynamics. We demonstrate physics-based editing on a wide range of examples producing myriad physical behavior while preserving geometric and visual consistency.</abstract><cop>Berlin/Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><doi>10.1007/s00371-018-1600-0</doi><tpages>16</tpages><orcidid>https://orcid.org/0000-0002-1752-3479</orcidid><orcidid>https://orcid.org/0000-0001-6342-2284</orcidid><orcidid>https://orcid.org/0000-0002-2661-505X</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 0178-2789
ispartof The Visual computer, 2020-01, Vol.36 (1), p.211-226
issn 0178-2789
1432-2315
1432-8726
language eng
recordid cdi_webofscience_primary_000511966800016
source SpringerNature Journals; Web of Science - Science Citation Index Expanded - 2020<img src="https://exlibris-pub.s3.amazonaws.com/fromwos-v2.jpg" />; Proquest Central; ProQuest Central UK/Ireland
subjects Alignment
Artificial Intelligence
Computer Graphics
Computer Science
Computer Science, Software Engineering
Editing
Geometry
Graphics
Human-Computer Interaction
Image Processing and Computer Vision
Original Article
Physical properties
Physics
Science & Technology
Simulation
Technology
title Calipso: physics-based image and video editing through CAD model proxies
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-04T04%3A49%3A24IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_webof&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Calipso:%20physics-based%20image%20and%20video%20editing%20through%20CAD%20model%20proxies&rft.jtitle=The%20Visual%20computer&rft.au=Haouchine,%20Nazim&rft.date=2020-01-01&rft.volume=36&rft.issue=1&rft.spage=211&rft.epage=226&rft.pages=211-226&rft.issn=0178-2789&rft.eissn=1432-2315&rft_id=info:doi/10.1007/s00371-018-1600-0&rft_dat=%3Cproquest_webof%3E2917937777%3C/proquest_webof%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2917937777&rft_id=info:pmid/&rfr_iscdi=true