• Home
  • SMPL-Model License
  • SMPL-Body License
  • Videos
  • Downloads
  • FAQ
SMPLSMPL
  • Home
  • SMPL-Model License
  • SMPL-Body License
  • Videos
  • Downloads
  • FAQ
  • Sign In
    Logout

SMPL

A Skinned Multi-Person Linear Model

Introduction

SMPL is a realistic 3D model of the human body that is based on skinning and blend shapes and is learned from thousands of 3D body scans. This site provides resources to learn about SMPL, including example FBX files with animated SMPL models, and code for using SMPL in Python, Maya and Unity.

Please register to download SMPL and related tools for using SMPL in different animation environments. After registration you will be able to access the Downloads menu at the top menubar.

For the latest upgrade to SMPL, check out the STAR Model (ECCV 2020) here: https://star.is.tue.mpg.de/

 

SMPL is also available with articulated hands and expressive faces, and can be estimated from images. Please find more information for these at the links below:
MANO & SMPL+H: http://mano.is.tue.mpg.de/
SMPL-X: https://smpl-x.is.tue.mpg.de/

You can download SMPL with up to 16 shape components, and in several standard versions (male, female, gender neutral). The original 300-dimension shape space of SMPL and related models (MANO, SMPL+H, SMPL-X) is available upon request. Please send your queries to: smpl@tue.mpg.de,  mano@tue.mpg.de or smplx@tuebingen.mpg.de.

Video

Authors

  • Matthew Loper
  • Naureen Mahmood
  • Javier Romero
  • Gerard Pons-Moll
  • Michael J. Black

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.

Information

  • Please register and agree to the license for access to the model and tools download section
  • Paper

News

19.10.2022
SMPL for Unreal Plugin (USMPL) is now available for download.
 
11.06.2021
SMPL for Blender add-on is now available for download.
 
21.01.2021
The full shape space of SMPL (300 Principal Component) is now available under the Downloads section.
 
04.11.2020
We now support conversion between all the models in the SMPL family, i.e. SMPL, SMPL+H, SMPL-X. https://github.com/vchoutas/smplx/tree/master/transfer_model
 
11.09.2020
Added SMPL UV map in OBJ format to Downloads.
 
25.08.2020
We released an updated version of SMPL for Python with all 300 shape parameters.
 
07.10.2019
Website moved to new content management system.
Please register again if you previously have registered on the old website.
 
10.12.2015
We released a version of SMPL for Python.
 
10.11.2015
Check out the new update (v 1.0.2) of our FBX files and Maya plugin.
 
04.11.2015
We have released a version of SMPL for Maya, which allows editing of body shape and pose. Also, you can now download sample animations that can be loaded in other packages like Blender or Unreal.
 
30.10.2015
The SMPL website is now live! Please register for access to the downloads section.

 

Referencing the Model

When using SMPL please reference:


@article{SMPL:2015,
      author = {Loper, Matthew and Mahmood, Naureen and Romero, Javier and Pons-Moll, Gerard and Black, Michael J.},
      title = {{SMPL}: A Skinned Multi-Person Linear Model},
      journal = {ACM Trans. Graphics (Proc. SIGGRAPH Asia)},
      month = oct,
      number = {6},
      pages = {248:1--248:16},
      publisher = {ACM},
      volume = {34},
      year = {2015}
    }
© 2020 Max-Planck-Gesellschaft -Imprint-Privacy Policy-License
RegisterSign In
© 2020 Max-Planck-Gesellschaft