Unlike previous models, the pose-dependent blend shapes are a linear function of the elements of the pose rotation matrices. 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. 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. 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.
SMPL distills thousand of body scans into a 3D statistical model of the human body with state-of-the-art realism (comparable to or better than much more complicated models), real time rendering, and full compatibility with standard animation software. In particular, SMPL is a realistic human body model that retains a simple .
To that end, we have developed a series of different 3D body models that can be used for both graphics and vision: BlendSCAPE , Delta, Dyna and SMPL.
Our Contour People (CP) model enables 2D pose inference methods while mantaining realistic body shapes more common to 3D models. The Stitched Puppet (SP) model taks an alternative approach towards efficient inference by exploiting the composability of human bodies into parts and performing message-passing inference.įinally, we are working towards modeling realistic virtual humans. Modeling bodies and performing inference with them is typically computationally expensive. Our research in human body models is driven towards a convergence between models used in Computer Vision and Computer Graphics: realistic and efficient models that are suitable for parameter inference from data. This problem has been tackled both in computer vision, with a long tradition of model-based methods for human detection and pose estimation, and graphics, where the ultimate goal is a faithful reproduction of real human bodies. We argue that making a computer able to model, perceive and generate human appearance would not only be clearly valuable in terms of practical applications, but would also entail a great step forward in the task of making computers perceive the world around us. The human body is highly articulated, deforms with kinematic changes, and exhibits large shape variability across subjects while clothes and hairstyles create a large variety of appearances.
In the process of teaching computers how to perceive the world, there is a family of objects that stands out due to its complexity and importance: human bodies. Organizational Leadership and Diversity.Locomotion in Biorobotic and Somatic Systems.Theory of Inhomogeneous Condensed Matter.