Expression flow for 3D-aware face component transfer

We address the problem of correcting an undesirable expression on a face photo by transferring local facial components, such as a smiling mouth, from another face photo of the same person which has the desired expression. Direct copying and blending using existing compositing tools results in semant...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:ACM SIGGRAPH 2011 papers 2011-07, Vol.30 (4), p.1-10
Hauptverfasser: Yang, Fei, Wang, Jue, Shechtman, Eli, Bourdev, Lubomir, Metaxas, Dimitri
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 10
container_issue 4
container_start_page 1
container_title ACM SIGGRAPH 2011 papers
container_volume 30
creator Yang, Fei
Wang, Jue
Shechtman, Eli
Bourdev, Lubomir
Metaxas, Dimitri
description We address the problem of correcting an undesirable expression on a face photo by transferring local facial components, such as a smiling mouth, from another face photo of the same person which has the desired expression. Direct copying and blending using existing compositing tools results in semantically unnatural composites, since expression is a global effect and the local component in one expression is often incompatible with the shape and other components of the face in another expression. To solve this problem we present Expression Flow, a 2D flow field which can warp the target face globally in a natural way, so that the warped face is compatible with the new facial component to be copied over. To do this, starting with the two input face photos, we jointly construct a pair of 3D face shapes with the same identity but different expressions. The expression flow is computed by projecting the difference between the two 3D shapes back to 2D. It describes how to warp the target face photo to match the expression of the reference photo. User studies suggest that our system is able to generate face composites with much higher fidelity than existing methods.
doi_str_mv 10.1145/1964921.1964955
format Article
fullrecord <record><control><sourceid>proquest_acm_b</sourceid><recordid>TN_cdi_proquest_miscellaneous_963870497</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>963870497</sourcerecordid><originalsourceid>FETCH-LOGICAL-a259t-14703cf7bd5fe5ec8356af48059c65c2592d8299699498d257cec1511ed004a93</originalsourceid><addsrcrecordid>eNqNkD1PwzAQhi0BElXpzJoNlpS72I5zIyrlQ6rEArPlOmepkMbFTlV-PoH2BzC9enXPe8MjxDXCHFHpO6RaUYXzv9T6TMzINOMBJJCSeC4mYCSUY8VLMcv5AwAQkXQtJ0Itv3eJc97EvghdPBQhpkI-lO7gEhfBeS583O5iz_1QDMn1OXC6EhfBdZlnp5yK98fl2-K5XL0-vSzuV6WrNA0lKgPSB7NudWDNvpG6dkE1oMnX2o9M1TYVUU2kqGkrbTx71IjcAihHcipujn93KX7tOQ92u8meu871HPfZUi0bA4rMSM6PpPNbu47xM1sE-6vHnvTYkx67ThsO4-D2nwP5A7FpYcM</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>963870497</pqid></control><display><type>article</type><title>Expression flow for 3D-aware face component transfer</title><source>Access via ACM Digital Library</source><creator>Yang, Fei ; Wang, Jue ; Shechtman, Eli ; Bourdev, Lubomir ; Metaxas, Dimitri</creator><contributor>Hoppe, Hugues</contributor><creatorcontrib>Yang, Fei ; Wang, Jue ; Shechtman, Eli ; Bourdev, Lubomir ; Metaxas, Dimitri ; Hoppe, Hugues</creatorcontrib><description>We address the problem of correcting an undesirable expression on a face photo by transferring local facial components, such as a smiling mouth, from another face photo of the same person which has the desired expression. Direct copying and blending using existing compositing tools results in semantically unnatural composites, since expression is a global effect and the local component in one expression is often incompatible with the shape and other components of the face in another expression. To solve this problem we present Expression Flow, a 2D flow field which can warp the target face globally in a natural way, so that the warped face is compatible with the new facial component to be copied over. To do this, starting with the two input face photos, we jointly construct a pair of 3D face shapes with the same identity but different expressions. The expression flow is computed by projecting the difference between the two 3D shapes back to 2D. It describes how to warp the target face photo to match the expression of the reference photo. User studies suggest that our system is able to generate face composites with much higher fidelity than existing methods.</description><identifier>ISSN: 0730-0301</identifier><identifier>ISBN: 9781450309431</identifier><identifier>ISBN: 1450309437</identifier><identifier>DOI: 10.1145/1964921.1964955</identifier><language>eng</language><publisher>New York, NY, USA: ACM</publisher><subject>Blending ; Compatibility ; Computing methodologies -- Artificial intelligence -- Computer vision -- Computer vision tasks ; Copying ; Facial ; Reproduction ; Three dimensional ; Two-dimensional flow ; Warp</subject><ispartof>ACM SIGGRAPH 2011 papers, 2011-07, Vol.30 (4), p.1-10</ispartof><rights>2011 ACM</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>309,310,314,780,784,27924,27925</link.rule.ids></links><search><contributor>Hoppe, Hugues</contributor><creatorcontrib>Yang, Fei</creatorcontrib><creatorcontrib>Wang, Jue</creatorcontrib><creatorcontrib>Shechtman, Eli</creatorcontrib><creatorcontrib>Bourdev, Lubomir</creatorcontrib><creatorcontrib>Metaxas, Dimitri</creatorcontrib><title>Expression flow for 3D-aware face component transfer</title><title>ACM SIGGRAPH 2011 papers</title><description>We address the problem of correcting an undesirable expression on a face photo by transferring local facial components, such as a smiling mouth, from another face photo of the same person which has the desired expression. Direct copying and blending using existing compositing tools results in semantically unnatural composites, since expression is a global effect and the local component in one expression is often incompatible with the shape and other components of the face in another expression. To solve this problem we present Expression Flow, a 2D flow field which can warp the target face globally in a natural way, so that the warped face is compatible with the new facial component to be copied over. To do this, starting with the two input face photos, we jointly construct a pair of 3D face shapes with the same identity but different expressions. The expression flow is computed by projecting the difference between the two 3D shapes back to 2D. It describes how to warp the target face photo to match the expression of the reference photo. User studies suggest that our system is able to generate face composites with much higher fidelity than existing methods.</description><subject>Blending</subject><subject>Compatibility</subject><subject>Computing methodologies -- Artificial intelligence -- Computer vision -- Computer vision tasks</subject><subject>Copying</subject><subject>Facial</subject><subject>Reproduction</subject><subject>Three dimensional</subject><subject>Two-dimensional flow</subject><subject>Warp</subject><issn>0730-0301</issn><isbn>9781450309431</isbn><isbn>1450309437</isbn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2011</creationdate><recordtype>article</recordtype><recordid>eNqNkD1PwzAQhi0BElXpzJoNlpS72I5zIyrlQ6rEArPlOmepkMbFTlV-PoH2BzC9enXPe8MjxDXCHFHpO6RaUYXzv9T6TMzINOMBJJCSeC4mYCSUY8VLMcv5AwAQkXQtJ0Itv3eJc97EvghdPBQhpkI-lO7gEhfBeS583O5iz_1QDMn1OXC6EhfBdZlnp5yK98fl2-K5XL0-vSzuV6WrNA0lKgPSB7NudWDNvpG6dkE1oMnX2o9M1TYVUU2kqGkrbTx71IjcAihHcipujn93KX7tOQ92u8meu871HPfZUi0bA4rMSM6PpPNbu47xM1sE-6vHnvTYkx67ThsO4-D2nwP5A7FpYcM</recordid><startdate>20110701</startdate><enddate>20110701</enddate><creator>Yang, Fei</creator><creator>Wang, Jue</creator><creator>Shechtman, Eli</creator><creator>Bourdev, Lubomir</creator><creator>Metaxas, Dimitri</creator><general>ACM</general><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20110701</creationdate><title>Expression flow for 3D-aware face component transfer</title><author>Yang, Fei ; Wang, Jue ; Shechtman, Eli ; Bourdev, Lubomir ; Metaxas, Dimitri</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a259t-14703cf7bd5fe5ec8356af48059c65c2592d8299699498d257cec1511ed004a93</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Blending</topic><topic>Compatibility</topic><topic>Computing methodologies -- Artificial intelligence -- Computer vision -- Computer vision tasks</topic><topic>Copying</topic><topic>Facial</topic><topic>Reproduction</topic><topic>Three dimensional</topic><topic>Two-dimensional flow</topic><topic>Warp</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yang, Fei</creatorcontrib><creatorcontrib>Wang, Jue</creatorcontrib><creatorcontrib>Shechtman, Eli</creatorcontrib><creatorcontrib>Bourdev, Lubomir</creatorcontrib><creatorcontrib>Metaxas, Dimitri</creatorcontrib><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>ACM SIGGRAPH 2011 papers</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yang, Fei</au><au>Wang, Jue</au><au>Shechtman, Eli</au><au>Bourdev, Lubomir</au><au>Metaxas, Dimitri</au><au>Hoppe, Hugues</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Expression flow for 3D-aware face component transfer</atitle><jtitle>ACM SIGGRAPH 2011 papers</jtitle><date>2011-07-01</date><risdate>2011</risdate><volume>30</volume><issue>4</issue><spage>1</spage><epage>10</epage><pages>1-10</pages><issn>0730-0301</issn><isbn>9781450309431</isbn><isbn>1450309437</isbn><abstract>We address the problem of correcting an undesirable expression on a face photo by transferring local facial components, such as a smiling mouth, from another face photo of the same person which has the desired expression. Direct copying and blending using existing compositing tools results in semantically unnatural composites, since expression is a global effect and the local component in one expression is often incompatible with the shape and other components of the face in another expression. To solve this problem we present Expression Flow, a 2D flow field which can warp the target face globally in a natural way, so that the warped face is compatible with the new facial component to be copied over. To do this, starting with the two input face photos, we jointly construct a pair of 3D face shapes with the same identity but different expressions. The expression flow is computed by projecting the difference between the two 3D shapes back to 2D. It describes how to warp the target face photo to match the expression of the reference photo. User studies suggest that our system is able to generate face composites with much higher fidelity than existing methods.</abstract><cop>New York, NY, USA</cop><pub>ACM</pub><doi>10.1145/1964921.1964955</doi><tpages>10</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0730-0301
ispartof ACM SIGGRAPH 2011 papers, 2011-07, Vol.30 (4), p.1-10
issn 0730-0301
language eng
recordid cdi_proquest_miscellaneous_963870497
source Access via ACM Digital Library
subjects Blending
Compatibility
Computing methodologies -- Artificial intelligence -- Computer vision -- Computer vision tasks
Copying
Facial
Reproduction
Three dimensional
Two-dimensional flow
Warp
title Expression flow for 3D-aware face component transfer
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T14%3A09%3A39IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_acm_b&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Expression%20flow%20for%203D-aware%20face%20component%20transfer&rft.jtitle=ACM%20SIGGRAPH%202011%20papers&rft.au=Yang,%20Fei&rft.date=2011-07-01&rft.volume=30&rft.issue=4&rft.spage=1&rft.epage=10&rft.pages=1-10&rft.issn=0730-0301&rft.isbn=9781450309431&rft.isbn_list=1450309437&rft_id=info:doi/10.1145/1964921.1964955&rft_dat=%3Cproquest_acm_b%3E963870497%3C/proquest_acm_b%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=963870497&rft_id=info:pmid/&rfr_iscdi=true