SMPL
Matthew Loper, Naureen Mahmood, Javier Romero et al. · ACM Transactions on Graphics · 2015
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.
Cited by 3,723 works. doi:10.1145/2816795.2818013
Authors
References
- SCAPE
- Pose space deformation
- The space of human body shapes
- The space of human body shapes
- OpenDR: An Approximate Differentiable Renderer
- Automatic rigging and animation of 3D characters
- Automatic rigging and animation of 3D characters
- FAUST: Dataset and Evaluation for 3D Mesh Registration
- Articulated body deformation from range scan data
- A Statistical Model of Human Pose and Body Shape