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:
Blends
Compatibility
Human
Mathematical models
Pipelines
Rendering
Three dimensional models
Transaction processing
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:0730-0301
1557-7368
DOI:10.1145/2816795.2818013