Parameterized model of 2D articulated human shape

摘要

A novel “contour person” (CP) model of the human body is proposed that has the expressive power of a detailed 3D model and the computational benefits of a simple 20 part-based model. The CP model is learned from a 3D model of the human body that captures natural shape and pose variations. The CP model factors deformations of the body into three components: shape variation, viewpoint change and pose variation. The CP model can be “dressed” with a low-dimensional clothing model. The clothing is represented as a deformation from the underlying CP representation. This deformation is learned from training examples using principal component analysis to produce so-called eigen-clothing. The coefficients of the eigen-clothing can be used to recognize different categories of clothing on dressed people. The parameters of the estimated 20 body can be used to discriminatively predict 3D body shape using a learned mapping approach.

主权项

1. A method, comprising:
generating, via a processor, a 2D contour person (CP) model of an unclothed human body based on a 3D model of a human body that captures natural shape and pose variations and a training set comprising projected contours and a segmentation of the contours into parts, wherein the 2D CP comprises a shape variation component, a viewpoint change component, and a pose variation component, wherein deformations are computed by aligning a first contour of a clothed human body with a second contour of the unclothed human body, and wherein an “eigen-clothing” model is learned using principal component analysis (PCA) applied to the deformations.