Parameterized model of 2D articulated human shape
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.
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.
2. The method of claim 1 , wherein the CP model is “clothed” by defining a set of linear coefficients that produce from a naked contour a deformation associated with a clothing type and therefrom model of the clothed human body.
3. The method of claim 1 , wherein the “eigen-clothing” is used to classify different types of clothing.
4. The method of claim 1 , further comprising deforming the “eigen-clothing” commensurate with shape and pose changes of the 2D CP model.
5. A non-transitory computer-readable storage device having stored therein instructions which, when executed by a processor, cause the processor to perform operations comprising:
generating 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.
6. The non-transitory computer-readable storage device of claim 5 , wherein the CP model is “clothed” by defining a set of linear coefficients that produce from the naked contour a deformation associated with a clothing type and therefrom model of the clothed human body.
7. The non-transitory computer-readable storage device of claim 5 , wherein the “eigen-clothing” is used to classify different types of clothing.
8. The non-transitory computer-readable storage device of claim 5 , storing additional instructions which, when executed by the processor, cause the processor to perform an operation further comprising deforming the “eigen-clothing” commensurate with shape and pose changes of the 2D CP model.
9. The non-transitory computer-readable storage device of claim 5 , storing additional instructions which, when executed by the processor, cause the processor to perform an operation further comprising generating the training set by projecting the contours and segmenting the contours into parts.
10. The non-transitory computer-readable storage device of claim 9 , wherein the contours correspond to at least one of the 3D model or the 2D CP model.
11. A system, comprising:
a processor; and
a non-transitory computer-readable storage medium having stored therein instructions which, when executed by the processor, cause the processor to perform operations comprising:
generating 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.
12. The system of claim 11 , wherein the CP model is “clothed” by defining a set of linear coefficients that produce from the naked contour a deformation associated with a clothing type and therefrom model of the clothed human body.
13. The system of claim 11 , wherein the “eigen-clothing” is used to classify different types of clothing.
14. The system of claim 11 , storing additional instructions which, when executed by the processor, cause the processor to perform an operation further comprising deforming the “eigen-clothing” commensurate with shape and pose changes of the 2D CP model.
15. The system of claim 11 , storing additional instructions which, when executed by the processor, cause the processor to perform an operation further comprising generating the training set by projecting the contours and segmenting the contours into parts.
16. The system of claim 11 , wherein the contours correspond to at least one of the 3D model or the 2D CP model.