Parameterized model of 2D articulated human shape
Disclosed are computer-readable devices, systems and methods for generating a model of a clothed body. The method includes generating a model of an unclothed human body, the model capturing a shape or a pose of the unclothed human body, determining two-dimensional contours associated with the model, and computing deformations by aligning a contour of a clothed human body with a contour of the unclothed human body. Based on the two-dimensional contours and the deformations, the method includes generating a first two-dimensional model of the unclothed human body, the first two-dimensional model factoring the deformations of the unclothed human body into one or more of a shape variation component, a viewpoint change, and a pose variation and learning an eigen-clothing model using principal component analysis applied to the deformations, wherein the eigen-clothing model classifies different types of clothing, to yield a second two-dimensional model of a clothed human body.
1. A method comprising:
generating a first two-dimensional body contour based at least on first image data representing a user in a first pose;
generating a second two-dimensional body contour based at least on second image data representing the user in a second pose;
receiving user data comprising at least one of a weight associated with the user or a height associated with the user;
identifying clothing deformation data associated with a garment;
generating a clothed model of the user, based at least on the first two-dimensional body contour, the second two-dimensional body contour, the user data, the clothing deformation data, and deformations of an unclothed human body that factors a shape variation component, a viewpoint change, and a pose variation; and
causing display of the clothed model of the user.
2. The method according to claim 1 , wherein the user data includes both the weight associated with the user and the height associated with the user.
3. The method according to claim 1 , further comprising generating a three-dimensional model of the unclothed human body that captures at least one of a shape or a pose of the unclothed human body.
4. The method according to claim 1 , further comprising computing the deformations of the unclothed human body by aligning a contour of the clothed model of the user with a contour of the unclothed human body.
5. The method according to claim 1 , wherein the first image data represents the user in a frontal view and the second image data represents the user in a non-frontal view.
6. The method according to claim 1 , wherein the pose variation comprises at least one of a body parts rotation and foreshortening.
7. The method according to claim 1 , wherein the deformations of the unclothed human body comprise non-rigid deformations resulting from articulation.
8. The method according to claim 1 , wherein the deformations of the unclothed human body is factored into a linear approximation to distortions caused by local camera view changes.
9. The method according to claim 1 , wherein the deformations of the unclothed human body is factored into an articulation of body parts represented by a rotation and length scaling.
10. The method according to claim 1 , wherein the deformations of the unclothed human body is factored into a linear model characterizing shape changes across a population.
11. A system comprising:
at least one processor; and
a non-transitory computer-readable storage medium having stored thereon instructions which, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
generating a first two-dimensional body contour based at least on first image data representing a user in a first pose;
generating a second two-dimensional body contour based at least on second image data representing the user in a second pose;
receiving user data comprising at least one of a weight associated with the user or a height associated with the user;
identifying clothing deformation data associated with a garment;
generating a clothed model of the user, based at least on the first two-dimensional body contour, the second two-dimensional body contour, the user data, the clothing deformation data, and deformations of an unclothed human body that factors a shape variation component, a viewpoint change, and a pose variation; and
causing display of the clothed model of the user.
12. The system according to claim 11 , wherein the user data includes both the weight associated with the user and the height associated with the user.
13. The system according to claim 11 , wherein the operations further comprise generating a three-dimensional model of the unclothed human body that captures at least one of a shape or a pose of the unclothed human body.
14. The system according to claim 11 , wherein the operations further comprise computing the deformations of the unclothed human body by aligning a contour of the clothed model of the user with a contour of the unclothed human body.
15. The system according to claim 11 , wherein the first image data represents the user in a frontal view and the second image data represents the user in a non-frontal view.
16. The system according to claim 11 , wherein the pose variation comprises at least one of a body parts rotation and foreshortening.
17. The system according to claim 11 , wherein the deformations of the unclothed human body comprise non-rigid deformations resulting from articulation.
18. The system according to claim 11 , wherein the deformations of the unclothed human body is factored into a linear approximation to distortions caused by local camera view changes.
19. The system according to claim 11 , wherein the deformations of the unclothed human body is factored into an articulation of body parts represented by a rotation and length scaling.
20. The system according to claim 11 , wherein the deformations of the unclothed human body is factored into a linear model characterizing shape changes across a population.