Loading…

SMPL: a skinned multi-person linear model

We present a learned model of human body shape and pose-dependent shape variation that is more accurate than previous models and is compatible with existing graphics pipelines. Our Skinned Multi-Person Linear model (SMPL) is a skinned vertex-based model that accurately represents a wide variety of b...

Full description

Saved in:
Bibliographic Details
Published in:ACM transactions on graphics 2015-11, Vol.34 (6), p.1-16
Main Authors: Loper, Matthew, Mahmood, Naureen, Romero, Javier, Pons-Moll, Gerard, Black, Michael J.
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites cdi_FETCH-LOGICAL-c228t-3c91547bc9c9b4f460224b0cd59de4c53103a9165305b498e39f4277bc6ac7c53
container_end_page 16
container_issue 6
container_start_page 1
container_title ACM transactions on graphics
container_volume 34
creator Loper, Matthew
Mahmood, Naureen
Romero, Javier
Pons-Moll, Gerard
Black, Michael J.
description We present a learned model of human body shape and pose-dependent shape variation that is more accurate than previous models and is compatible with existing graphics pipelines. Our Skinned Multi-Person Linear model (SMPL) is a skinned vertex-based model that accurately represents a wide variety of body shapes in natural human poses. The parameters of the model are learned from data including the rest pose template, blend weights, pose-dependent blend shapes, identity-dependent blend shapes, and a regressor from vertices to joint locations. Unlike previous models, the pose-dependent blend shapes are a linear function of the elements of the pose rotation matrices. This simple formulation enables training the entire model from a relatively large number of aligned 3D meshes of different people in different poses. We quantitatively evaluate variants of SMPL using linear or dual-quaternion blend skinning and show that both are more accurate than a Blend-SCAPE model trained on the same data. We also extend SMPL to realistically model dynamic soft-tissue deformations. Because it is based on blend skinning, SMPL is compatible with existing rendering engines and we make it available for research purposes.
doi_str_mv 10.1145/2816795.2818013
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1793238038</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1793238038</sourcerecordid><originalsourceid>FETCH-LOGICAL-c228t-3c91547bc9c9b4f460224b0cd59de4c53103a9165305b498e39f4277bc6ac7c53</originalsourceid><addsrcrecordid>eNotj8tKAzEUhoNUcKyufQU3ac_JObktpXiDEYXWdcikGahMnTppF769I53Vt_gv8Alxh7BAZL1UDo31ejHSAdKFqFBrKy0ZNxMVWAIJBHglrkv5AgDDbCoxW7991Dfiso1dybcT5-Lz6XGzepH1-_Pr6qGWSSl3lJQ8arZN8sk33LIBpbiBtNV-mzlpQqDo0WgC3bB3mXzLyo4DE5Md87m4P_8ehv7nlMsx7Hcl5a6L37k_lYDWkyIH5Mbq8lxNQ1_KkNtwGHb7OPwGhPDvGybfMPnSH-rUQ5o</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1793238038</pqid></control><display><type>article</type><title>SMPL: a skinned multi-person linear model</title><source>Association for Computing Machinery:Jisc Collections:ACM OPEN Journals 2023-2025 (reading list)</source><creator>Loper, Matthew ; Mahmood, Naureen ; Romero, Javier ; Pons-Moll, Gerard ; Black, Michael J.</creator><creatorcontrib>Loper, Matthew ; Mahmood, Naureen ; Romero, Javier ; Pons-Moll, Gerard ; Black, Michael J.</creatorcontrib><description>We present a learned model of human body shape and pose-dependent shape variation that is more accurate than previous models and is compatible with existing graphics pipelines. Our Skinned Multi-Person Linear model (SMPL) is a skinned vertex-based model that accurately represents a wide variety of body shapes in natural human poses. The parameters of the model are learned from data including the rest pose template, blend weights, pose-dependent blend shapes, identity-dependent blend shapes, and a regressor from vertices to joint locations. Unlike previous models, the pose-dependent blend shapes are a linear function of the elements of the pose rotation matrices. This simple formulation enables training the entire model from a relatively large number of aligned 3D meshes of different people in different poses. We quantitatively evaluate variants of SMPL using linear or dual-quaternion blend skinning and show that both are more accurate than a Blend-SCAPE model trained on the same data. We also extend SMPL to realistically model dynamic soft-tissue deformations. Because it is based on blend skinning, SMPL is compatible with existing rendering engines and we make it available for research purposes.</description><identifier>ISSN: 0730-0301</identifier><identifier>EISSN: 1557-7368</identifier><identifier>DOI: 10.1145/2816795.2818013</identifier><language>eng</language><subject>Blends ; Compatibility ; Human ; Mathematical models ; Pipelines ; Rendering ; Three dimensional models ; Transaction processing</subject><ispartof>ACM transactions on graphics, 2015-11, Vol.34 (6), p.1-16</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c228t-3c91547bc9c9b4f460224b0cd59de4c53103a9165305b498e39f4277bc6ac7c53</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Loper, Matthew</creatorcontrib><creatorcontrib>Mahmood, Naureen</creatorcontrib><creatorcontrib>Romero, Javier</creatorcontrib><creatorcontrib>Pons-Moll, Gerard</creatorcontrib><creatorcontrib>Black, Michael J.</creatorcontrib><title>SMPL: a skinned multi-person linear model</title><title>ACM transactions on graphics</title><description>We present a learned model of human body shape and pose-dependent shape variation that is more accurate than previous models and is compatible with existing graphics pipelines. Our Skinned Multi-Person Linear model (SMPL) is a skinned vertex-based model that accurately represents a wide variety of body shapes in natural human poses. The parameters of the model are learned from data including the rest pose template, blend weights, pose-dependent blend shapes, identity-dependent blend shapes, and a regressor from vertices to joint locations. Unlike previous models, the pose-dependent blend shapes are a linear function of the elements of the pose rotation matrices. This simple formulation enables training the entire model from a relatively large number of aligned 3D meshes of different people in different poses. We quantitatively evaluate variants of SMPL using linear or dual-quaternion blend skinning and show that both are more accurate than a Blend-SCAPE model trained on the same data. We also extend SMPL to realistically model dynamic soft-tissue deformations. Because it is based on blend skinning, SMPL is compatible with existing rendering engines and we make it available for research purposes.</description><subject>Blends</subject><subject>Compatibility</subject><subject>Human</subject><subject>Mathematical models</subject><subject>Pipelines</subject><subject>Rendering</subject><subject>Three dimensional models</subject><subject>Transaction processing</subject><issn>0730-0301</issn><issn>1557-7368</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2015</creationdate><recordtype>article</recordtype><recordid>eNotj8tKAzEUhoNUcKyufQU3ac_JObktpXiDEYXWdcikGahMnTppF769I53Vt_gv8Alxh7BAZL1UDo31ejHSAdKFqFBrKy0ZNxMVWAIJBHglrkv5AgDDbCoxW7991Dfiso1dybcT5-Lz6XGzepH1-_Pr6qGWSSl3lJQ8arZN8sk33LIBpbiBtNV-mzlpQqDo0WgC3bB3mXzLyo4DE5Md87m4P_8ehv7nlMsx7Hcl5a6L37k_lYDWkyIH5Mbq8lxNQ1_KkNtwGHb7OPwGhPDvGybfMPnSH-rUQ5o</recordid><startdate>20151101</startdate><enddate>20151101</enddate><creator>Loper, Matthew</creator><creator>Mahmood, Naureen</creator><creator>Romero, Javier</creator><creator>Pons-Moll, Gerard</creator><creator>Black, Michael J.</creator><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20151101</creationdate><title>SMPL</title><author>Loper, Matthew ; Mahmood, Naureen ; Romero, Javier ; Pons-Moll, Gerard ; Black, Michael J.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c228t-3c91547bc9c9b4f460224b0cd59de4c53103a9165305b498e39f4277bc6ac7c53</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2015</creationdate><topic>Blends</topic><topic>Compatibility</topic><topic>Human</topic><topic>Mathematical models</topic><topic>Pipelines</topic><topic>Rendering</topic><topic>Three dimensional models</topic><topic>Transaction processing</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Loper, Matthew</creatorcontrib><creatorcontrib>Mahmood, Naureen</creatorcontrib><creatorcontrib>Romero, Javier</creatorcontrib><creatorcontrib>Pons-Moll, Gerard</creatorcontrib><creatorcontrib>Black, Michael J.</creatorcontrib><collection>CrossRef</collection><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 transactions on graphics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Loper, Matthew</au><au>Mahmood, Naureen</au><au>Romero, Javier</au><au>Pons-Moll, Gerard</au><au>Black, Michael J.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>SMPL: a skinned multi-person linear model</atitle><jtitle>ACM transactions on graphics</jtitle><date>2015-11-01</date><risdate>2015</risdate><volume>34</volume><issue>6</issue><spage>1</spage><epage>16</epage><pages>1-16</pages><issn>0730-0301</issn><eissn>1557-7368</eissn><abstract>We present a learned model of human body shape and pose-dependent shape variation that is more accurate than previous models and is compatible with existing graphics pipelines. Our Skinned Multi-Person Linear model (SMPL) is a skinned vertex-based model that accurately represents a wide variety of body shapes in natural human poses. The parameters of the model are learned from data including the rest pose template, blend weights, pose-dependent blend shapes, identity-dependent blend shapes, and a regressor from vertices to joint locations. Unlike previous models, the pose-dependent blend shapes are a linear function of the elements of the pose rotation matrices. This simple formulation enables training the entire model from a relatively large number of aligned 3D meshes of different people in different poses. We quantitatively evaluate variants of SMPL using linear or dual-quaternion blend skinning and show that both are more accurate than a Blend-SCAPE model trained on the same data. We also extend SMPL to realistically model dynamic soft-tissue deformations. Because it is based on blend skinning, SMPL is compatible with existing rendering engines and we make it available for research purposes.</abstract><doi>10.1145/2816795.2818013</doi><tpages>16</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0730-0301
ispartof ACM transactions on graphics, 2015-11, Vol.34 (6), p.1-16
issn 0730-0301
1557-7368
language eng
recordid cdi_proquest_miscellaneous_1793238038
source Association for Computing Machinery:Jisc Collections:ACM OPEN Journals 2023-2025 (reading list)
subjects Blends
Compatibility
Human
Mathematical models
Pipelines
Rendering
Three dimensional models
Transaction processing
title SMPL: a skinned multi-person linear model
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T17%3A05%3A43IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=SMPL:%20a%20skinned%20multi-person%20linear%20model&rft.jtitle=ACM%20transactions%20on%20graphics&rft.au=Loper,%20Matthew&rft.date=2015-11-01&rft.volume=34&rft.issue=6&rft.spage=1&rft.epage=16&rft.pages=1-16&rft.issn=0730-0301&rft.eissn=1557-7368&rft_id=info:doi/10.1145/2816795.2818013&rft_dat=%3Cproquest_cross%3E1793238038%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c228t-3c91547bc9c9b4f460224b0cd59de4c53103a9165305b498e39f4277bc6ac7c53%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1793238038&rft_id=info:pmid/&rfr_iscdi=true