System and method for simulating realistic clothing

1. A method comprising:

generating, via a processor, a clothing deformation model for a clothing type, wherein the clothing deformation model factors a change of clothing shape for the clothing type to represent rigid rotation of cloth pieces, pose-independent clothing shape variations induced by clothing size and underlying body shape parameters, and pose-dependent non-rigid deformations, wherein:

the clothing deformation model is a learned model based on training pose data:

the pose-independent clothing shape variations are learned from a shape training set having human bodies with different shapes wearing the clothing type in a same pose;

the pose-dependent non-rigid deformations are learned from a pose training set having a human body wearing the clothing type in different poses; and

the pose-independent clothing shape variations are calculated separately from the pose-dependent non-rigid deformations before combining the rigid rotation, clothing shape variations, and the non-deformations into a resulting clothing shape;

generating, via the processor, for an input human body, a custom-shaped garment associated with the clothing type by mapping, via the clothing deformation model, body shape parameters of the input human body to clothing shape parameters of the clothing type; and

automatically, via the processor, dressing the input human body with the custom-shaped garment.

2. The method of claim 1 , wherein the input human body comprises a parameterized model of a human body with known shape and pose parameters.

3. The method of claim 1 , wherein the clothing deformation model automatically adapts to new bodies.

4. The method of claim 1 , wherein automatically dressing the input human body comprises simulating realistic clothing on the input human body without manual intervention.

5. The method of claim 1 , wherein the clothing deformation model allows realistic clothing to be simulated on a plurality of characters or bodies and in any pose.

6. The method of claim 1 , wherein the clothing type comprises at least one of a T-shirt, a long-sleeved shirt, a skirt, a sweater, a coat, a jacket, an undershirt, shorts, or long pants.

7. The method of claim 1 , wherein automatically dressing the input human body comprises warping the custom-shaped garment to lay entirely outside the input human body.

8. The method of claim 7 , wherein warping the custom-shaped garment comprises minimizing a measure of cloth-body interpenetration with respect to vertices associated with the custom-shaped garment.

9. The method of claim 8 , wherein warping the custom-shaped garment further comprises regularizing the custom-shaped garment to make the custom-shaped garment deform plausibly.

10. The method of claim 1 , further comprising:

based on the clothing deformation model, generating custom-shaped garments for a plurality of bodies having a plurality of shapes and poses; and

automatically dressing the plurality of bodies with the custom-shaped garments.

11. A system comprising:

a processor; and

a computer-readable storage medium having stored therein instructions which, when executed by the processor, cause the processor to perform operations comprising:

generating a clothing deformation model for a clothing type, wherein the clothing deformation model factors a change of clothing shape for the clothing type to represent rigid rotation of cloth pieces, pose-independent clothing shape variations induced by clothing size and underlying body shape parameters, and pose-dependent non-rigid deformations, wherein:

the clothing deformation model is a learned model based on training pose data;

the pose-independent clothing shape variations are learned from a shape training set having human bodies with different shapes wearing the clothing type in a same pose;

the pose-dependent non-rigid deformations are learned from a pose training set having a human body wearing the clothing type in different poses; and

the pose-independent clothing shape variations are calculated separately from the pose-dependent non-regid deformations before combining the rigid rotation, clothing shape variations, and non-rigid deformations into a resulting clothing shape;

generating, for an input human body, a custom-shaped garment associated the clothing type by mapping, via the clothing deformation model, body shape parameters of the input human body to clothing shape parameters of the clothing type; and

automatically dressing the input human body with the custom-shaped garment.

12. The system of claim 11 , wherein the input human body comprises a parameterized model of a human body with known shape and pose parameters.

13. The system of claim 11 , wherein the clothing type comprises at least one of a T-shirt, a long-sleeved shirt, a skirt, a sweater, a coat, a jacket, an undershirt, shorts, and long pants.

14. The system of claim 11 , wherein the computer-readable storage medium stores additional instructions which, when executed by the processor, cause the processor to perform additional operations comprising automatically dressing the input human body, and further cause the processor to perform operations comprising:

warping the custom-shaped garment to lay entirely outside the input human body, and

wherein the instructions, when executed by the processor to perform operations comprising warping the custom-shaped garment, further cause the processor to perform operations comprising minimizing a measure of cloth-body interpenetration with respect to vertices associated with the custom-shaped garment.

15. The system of claim 11 , wherein the computer-readable storage medium stores additional instructions which, when executed by the processor, further cause the processor to perform operations comprising:

based on the clothing deformation model, generating custom-shaped garments for a plurality of bodies having a plurality of shapes and poses; and

automatically dressing the plurality of bodies with the custom-shaped garments.

16. A non-transitory computer-readable storage medium having stored therein instructions which, when executed by a processor, cause the processor to perform operations comprising:

generating a clothing deformation model for a clothing type, wherein the clothing deformation model factors a change of clothing shape for the clothing type to represent rigid rotation of cloth pieces, pose-independent clothing shape variations induced by clothing size and underlying body shape parameters, and pose-dependent non-rigid deformations, wherein:

the clothing deformation model is a learned based on training pose data;

the pose-independent clothing shape variations are learned from a shape training set having human bodies with different shapes wearing the clothing type in a same pose;

the pose-dependent non-rigid deformations are learned from a pose training set having a human body wearing the clothing type in dirrerent poses; and

the pose-independent clothing shape variations are calculated separately from the pose-dependent non-rigid deformations before combining the rigid rotation, clothing shape variations, and non-rigid deformations into a resulting clothing shape;

generating, for an input human body, a custom-shaped garment associated with the clothing type by mapping, via the clothing deformation model, body shape parameters of the input human body to clothing shape parameters for the clothing type; and

automatically dressing the input human body with the custom-shaped garment.

17. The non-transitory computer-readable storage medium of claim 16 , wherein the input human body comprises a parameterized model of a human body with known shape and pose parameters.

18. The non-transitory computer-readable storage medium of claim 16 , wherein the instructions, when executed by the processor, further cause the processor to perform operations comprising:

based on the clothing deformation model, generating custom-shaped garments for a plurality of bodies having a plurality of shapes and poses; and

automatically dressing the plurality of bodies with the custom-shaped garments.

19. The non-transitory computer-readable storage medium of claim 16 , wherein the non-transitory computer-readable storage medium stores additional instructions which, when executed by the processor, cause the processor to perform operations comprising automatically dressing the input human body, and further cause the processor to perform operations comprising:

warping the custom-shaped garment to lay entirely outside the input human body, and

wherein the instructions, when executed by the processor to perform operations comprising warping the custom-shaped garment, further cause the processor to perform operations comprising minimizing a measure of cloth-body interpenetration with respect to vertices associated with the custom-shaped garment.