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. You can then download SMPL with up to 300 shape components, and in several standard versions (male, female, gender neutral).
Other Human Body Models
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 (SIGGRAPH Asia 2017): https://mano.is.tue.mpg.de/
- Articulated hands
- SMPL-X (CVPR 2019) : https://smpl-x.is.tue.mpg.de/
- Articulated hands and expressive face
Additional human body models are available on the following websites:
- STAR (ECCV 2020): https://star.is.tue.mpg.de/
- STAR is a compact realistic model of the human body, with learned sparse spatially local corrective blend shapes, that is is a drop in replacement for SMPL
- SUPR (ECCV 2022): https://supr.is.tue.mpg.de/
- SUPR is a factorized representation of the human body that can be separated into a full suite of body part models, including a novel human foot model with learned contact deformations. In contrast to existing body part models such as FLAME and MANO, the separated body part models are able to capture the full range of head and hand motion.
Please use the contact information on those websites for further enquiries about these models.
Video:
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.
News
Please register again if you previously have registered on the old website.
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}
}
Contact
For questions, please contact smpl@tue.mpg.de
For commercial licensing, please contact sales@meshcapade.com