SMPL: a skinned multi-person linear model

@article{Loper2015SMPLAS,
  title={SMPL: a skinned multi-person linear model},
  author={Matthew Loper and Naureen Mahmood and Javier Romero and Gerard Pons-Moll and Michael J. Black},
  journal={ACM Trans. Graph.},
  year={2015},
  volume={34},
  pages={248:1-248:16}
}
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… Expand
STAR: Sparse Trained Articulated Human Body Regressor
TLDR
This work defines per-joint pose correctives and learns the subset of mesh vertices that are influenced by each joint movement that results in more realistic deformations and significantly reduces the number of model parameters to 20% of SMPL. Expand
Parametric Human Shape Reconstruction via Bidirectional Silhouette Guidance
TLDR
This work presents a method to reconstruct the body geometry of a person by aligning the skinned multi-person linear (SMPL) model to an unconstrained human image and proposes a novel bidirectional silhouette constraint to restrict the estimated body geometry. Expand
Unsupervised Shape and Pose Disentanglement for 3D Meshes
TLDR
A combination of self-consistency and cross- Consistency constraints to learn pose and shape space from registered meshes and incorporates as-rigid-as-possible deformation(ARAP) into the training loop to avoid degenerate solutions. Expand
Detailed Human Shape Estimation From a Single Image by Hierarchical Mesh Deformation
TLDR
A novel learning-based framework that combines the robustness of parametric model with the flexibility of free-form 3D deformation and is able to restore detailed human body shapes beyond skinned models is proposed. Expand
Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies
TLDR
A unified deformation model is presented for the markerless capture of human movement at multiple scales, including facial expressions, body motion, and hand gestures, which enables the full expression of part movements by a single seamless model. Expand
3DPeople: Modeling the Geometry of Dressed Humans
TLDR
A multi-resolution deep generative network is designed that, given an input image of a dressed human, predicts his/her geometry image (and thus the clothed body shape) in an end-to-end manner, both for synthetic validation and on the wild images. Expand
Parametric Model-Based 3D Human Shape and Pose Estimation from Multiple Views
TLDR
This paper presents a novel method for estimating 3D human body pose and shape from several RGB images, using detected joint positions in the images and based on a parametric human body model. Expand
BodyNet: Volumetric Inference of 3D Human Body Shapes
TLDR
BodyNet is an end-to-end trainable network that benefits from a volumetric 3D loss, a multi-view re-projection loss, and intermediate supervision of 2D pose, 2D body part segmentation, and 3D pose and achieves state-of-the-art performance. Expand
Tex2Shape: Detailed Full Human Body Geometry From a Single Image
TLDR
This work presents a simple yet effective method to infer detailed full human body shape from only a single photograph, trained purely with synthetic data, and generalizes well to real-world photographs. Expand
Markerless Multiview Motion Capture with 3D Shape Model Adaptation
TLDR
This paper addresses simultaneous markerless motion and shape capture from 3D input meshes of partial views onto a moving subject and uses a computer graphics model based on kinematic skinning as template tracking model, representing true human shape and kinematics‐based shape deformations. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 61 REFERENCES
Learning a correlated model of identity and pose-dependent body shape variation for real-time synthesis
TLDR
This model is the first to capture both identity-dependent and pose-dependent shape variation in a correlated fashion, enabling creation of a variety of virtual human characters with realistic and non-linear body deformations that are customized to the individual. Expand
Tensor-Based Human Body Modeling
TLDR
A novel approach to model 3D human body with variations on both human shape and pose, by exploring a tensor decomposition technique, which outperforms the SCAPE model quite significantly. Expand
SCAPE: shape completion and animation of people
TLDR
The SCAPE method is capable of constructing a high-quality animated surface model of a moving person, with realistic muscle deformation, using just a single static scan and a marker motion capture sequence of the person. Expand
Spherical blend skinning: a real-time deformation of articulated models
TLDR
A new algorithm is presented which removes shortcomings of the most widely used skeletal animation algorithm while maintaining almost the same time and memory complexity as the linear blend skinning, and minimizes the cost of upgrade from linear to spherical blendskinning in many existing applications. Expand
Learning skeletons for shape and pose
TLDR
This paper presents a method for estimating a rigid skeleton, including skinning weights, skeleton connectivity, and joint positions, given a sparse set of example poses, and presents an approach for synthesizing a suitable bind shape that additionally improves the accuracy of the generated model. Expand
The space of human body shapes: reconstruction and parameterization from range scans
TLDR
With this parameterized set, a variety of applications for human body modeling are explored, including: morphing, texture transfer, statistical analysis of shape, model fitting from sparse markers, feature analysis to modify multiple correlated parameters, and transfer of surface detail and animation controls from a template to fitted models. Expand
A Statistical Model of Human Pose and Body Shape
TLDR
A unified model that describes both, human pose and body shape is introduced which allows us to accurately model muscle deformations not only as a function of pose but also dependent on the physique of the subject. Expand
Dyna: a model of dynamic human shape in motion
TLDR
The Dyna model realistically represents the dynamics of soft tissue for previously unseen subjects and motions and provides tools for animators to modify the deformations and apply them to new stylized characters. Expand
Smooth skinning decomposition with rigid bones
TLDR
The Smooth Skinning Decomposition with Rigid Bones (SSDR), an automated algorithm to extract the linear blend skinning (LBS) from a set of example poses, can measurably outperform the state-of-the-art skinning decomposition schemes in terms of accuracy and applicability. Expand
Coregistration: Simultaneous Alignment and Modeling of Articulated 3D Shape
TLDR
By minimizing a single objective function, the model reliably obtain high quality registration of noisy, incomplete, laser scans, while simultaneously learning a highly realistic articulated body model that greatly improves robustness to noise and missing data. Expand
...
1
2
3
4
5
...