IP Library › Granted Patent US 10,134,181
Granted Patent B2
US 10,134,181 · App. 15/620,614 · Granted Nov 20, 2018

System and method for simulating realistic clothing

Inventors: Michael J. Black (Tuebingen, DE); Peng Guan (Mountain View, CA)
Assignee: BROWN UNIVERSITY
G06T17/00G06F17/5009G06T19/20G06F2217/32G06T2210/16G06T2219/2016G06T2219/2021
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,134,181
App. No.
15/620,614
Granted
Nov 20, 2018
Kind
B2
Abstract

A system generates a clothing deformation model which models one or more of a pose-dependent clothing shape variation which is induced by underlying body pose parameters, a pose-independent clothing shape variation which is induced by clothing size and underlying body shape parameters and a clothing shape variation including a combination of the pose-dependent clothing shape variation and/or the pose-independent clothing shape variation. The system generates, for an input human body, a custom-shaped garment associated with a 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 dresses the input human body with the custom-shaped garment.

Claims (37)

1. A method comprising:

generating, via a processor, a clothing deformation model for a clothing type, the clothing deformation model factoring:

a pose-dependent clothing shape variation which is induced by underlying body pose parameters, wherein a pose-dependent clothing deformation model comprises a learned model based on a pose training set having one or more human bodies wearing the clothing type in various poses;

a pose-independent clothing shape variation which is induced by clothing size and underlying body shape parameters, wherein a pose-independent clothing deformation model comprises a learned model based on a shape training set having human bodies with different shapes wearing the clothing type in a same pose as each other; and

a clothing shape variation comprising a combination of the pose-dependent clothing shape variation and the pose-independent clothing shape variation; and

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 pose-dependent clothing shape variation is comprised of non-rigid deformations and combined using a combining method with rigid rotation of cloth pieces.

3. The method of claim 1 , wherein the input human body is automatically dressed with clothing learned from simulated clothing data.

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

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

6. The method of claim 1 , wherein the pose-dependent clothing shape variation is composed of rigid rotations combined with learned deformations.

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

8. 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.

9. 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.

10. 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.

11. The method of claim 5 , wherein warping the custom-shaped garment comprises minimizing a measure of cloth-body interpenetration with respect to vertices associated with the custom-shaped garment.

12. The method of claim 6 , wherein warping the custom-shaped garment further comprises regularizing the custom-shaped garment to make the custom-shaped garment deform plausibly.

13. 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.

14. 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, the clothing deformation model factoring:

a pose-dependent clothing shape variation which is induced by underlying body pose parameters, wherein a pose-dependent clothing deformation model comprises a learned model based on a pose training set having one or more human bodies wearing the clothing type in various poses;

a pose-independent clothing shape variation which is induced by clothing size and underlying body shape parameters, wherein a pose-independent clothing deformation model comprises a learned model based on a shape training set having human bodies with different shapes wearing the clothing type in a same pose as each other; and

a clothing shape variation comprising a combination of the pose-dependent clothing shape variation and the pose-independent clothing shape variation;

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 of the clothing type; and

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

15. 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, the clothing deformation model factoring:

a pose-dependent clothing shape variation which is induced by underlying body pose parameters, wherein a pose-dependent clothing deformation model comprises a learned model based on a pose training set having one or more human bodies wearing the clothing type in various poses;

a pose-independent clothing shape variation which is induced by clothing size and underlying body shape parameters, wherein a pose-independent clothing deformation model comprises a learned model based on a shape training set having human bodies with different shapes wearing the clothing type in a same pose as each other; and

a clothing shape variation comprising a combination of the pose-dependent clothing shape variation and the pose-independent clothing shape variation;

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 of the clothing type; and

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

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 27, 2018
From: BLACK, MICHAEL J.; GUAN, PENG
To: BROWN UNIVERSITY
Reel/Frame 046483/0177 →
Continuity (3)
Continuation In Part 14372140
Provisional Application 61599533 · Feb 16, 2012
Related Publication 20170323476A1 · Nov 9, 2017