Avatar-based virtual dressing room

• US 9,646,340 B2
• Filed: 08/02/2012
• Issued: 05/09/2017
• Est. Priority Date: 04/01/2010
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Kapur, Jay, Jones, Sheridan, Tsunoda, Kudo
• Primary Examiner(s): GEORGALAS, ANNE MARIE
• Application Number:
  US13/565,586
• Publication Number:
  US 20120299912A1
• Time in Patent Office: 1,741 Days
• CPC Class Codes: G06F 3/011 Arrangements for interaction with the human body, e.g. for user immersion in virtual reality blind teaching G09B21/00
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0641 Shopping interfaces
• CPC Class Codes: G06Q 30/0643 Graphical representation of items or shoppers
• CPC Class Codes: G06T 15/00 3D [Three Dimensional] image rendering
• CPC Class Codes: G06T 17/20 Finite element generation, e.g. wire-frame surface description, tesselation
• CPC Class Codes: G06T 19/20 Editing of 3D images, e.g. changing shapes or colours, aligning objects or positioning parts

Abstract

A method to help a user visualize how a wearable article will look on the user'"'"'s body. Enacted on a computing system, the method includes receiving an image of the user'"'"'s body from an image-capture component. Based on the image, a posable, three-dimensional, virtual avatar is constructed to substantially resemble the user. In this example method, data is obtained that identifies the wearable article as being selected for the user. This data includes a plurality of metrics that at least partly define the wearable article. Then, a virtualized form of the wearable article is attached to the avatar, which is provided to a display component for the user to review.

Claims

1. In a computing system having a computer operatively coupled to a depth camera, a method to help a subject visualize how a wearable article will look on the subject, the method comprising:

receiving with the computer a depth map of the subject, the depth map acquired by the depth camera;

obtaining with the computer a virtual skeleton of the subject based on the depth map;

harvesting from the virtual skeleton by the computer a set of subject metrics corresponding to distances between predetermined points of the virtual skeleton;

providing the subject metrics as input to an engine of the computer configured to output a virtual body mesh as a function of the subject metrics;

refining the virtual body mesh by the computer, by varying the subject metrics to decrease distance between points on the depth map and corresponding points of the virtual body mesh, the refined virtual body mesh being a basis for a posable, three-dimensional, virtual avatar resembling the subject;

obtaining at the computer data that identifies the wearable article as being selected for the subject, the data including a plurality of article metrics at least partly defining the wearable article;

attaching by the computer a virtualized form of the wearable article to the avatar; and

providing the avatar, with the virtualized form of the wearable article attached, from the computer to a display component of the computing system, for the subject to review.

2. The method of claim 1 wherein the wearable article is selected for the subject via input from a person other than the subject.

3. The method of claim 2 further comprising providing a mechanism for the subject to request the input from the person other than the subject.

4. The method of claim 2 wherein the input includes an indication of one or more outfits worn by the person other than the subject.

5. The method of claim 4 further comprising selecting the person other than the subject as someone exhibiting purchasing behavior similar to that of the subject, with respect to wearable articles.

6. The method of claim 1 wherein the wearable article is selected by an automated service of a vendor of the wearable article.

7. The method of claim 1 wherein the wearable article is selected via a selection engine of the computer, the selection engine being configured to select the wearable article from an inventory of articles accessible to the subject.

8. The method of claim 7 wherein the inventory of articles accessible to the subject includes articles for sale to the subject.

9. The method of claim 7 wherein the inventory of articles accessible to the subject includes articles in a wardrobe of the subject.

10. The method of claim 9 wherein the inventory of articles accessible to the subject excludes articles currently unavailable for wearing, the method further comprising tracking a plurality of articles in the wardrobe to determine which items are currently unavailable for wearing.

11. The method of claim 9 wherein the inventory of articles accessible to the subject excludes articles worn by the subject above a threshold frequency, the method further comprising tracking a plurality of articles in the wardrobe to determine how frequently each item has been worn.

12. The method of claim 7 wherein the wearable article is a first wearable article, and wherein the selection engine is configured to select the first wearable article based on one or more of color, style, and brand matching with respect to a second wearable article.

13. The method of claim 12 wherein the second wearable article is an article already selected by the subject for wearing or purchase.

14. The method of claim 12 wherein the second wearable article is an article in a wardrobe of the subject.

15. The method of claim 7 wherein the selection engine is configured to select the wearable article based on current or predicted weather in a locality of the subject.

16. The method of claim 1 wherein providing the avatar to the display component includes providing the avatar of the subject together with an avatar of a person other than the subject.

17. The method of claim 1 further comprising receiving an image of the subject while wearing the wearable article and saving that image for the subject to review.

18. Enacted on a computing system including a computer operatively coupled to a depth camera, a method to help a subject visualize how a wearable article will look on the subject, the method comprising:

receiving with the computer a depth map of the subject, the depth map acquired by the depth camera;

obtaining with the computer a virtual skeleton of the subject based on the depth map;

harvesting from the virtual skeleton by the computer a set of subject metrics corresponding to distances between predetermined points of the virtual skeleton;

providing the subject metrics as input to an engine of the computer configured to output a virtual body mesh as a function of the subject metrics;

refining the virtual body mesh by the computer by varying the subject metrics to decrease distance between points on the depth map and corresponding points of the virtual body mesh, the refined virtual body mesh being a basis for a posable, three-dimensional, virtual avatar resembling the subject;

providing by the computer a mechanism for the subject to request input from a person other than the subject, regarding selection of the wearable article;

obtaining at the computer data that identifies the wearable article as being selected for the subject via input from the person other than the subject, the data including a plurality of article metrics that at least partly define the wearable article;

attaching by the computer a virtualized form of the wearable article to the avatar; and

providing the avatar, with the virtualized form of the wearable article attached, from the computer to a display component for the subject to review.

19. Enacted on a computing system including a computer operatively coupled to a depth camera, a method to guide a user through purchase of a wearable first article, the method comprising:

receiving with the computer a depth map of the subject, the depth map acquired by the depth camera;

obtaining with the computer a virtual skeleton of the subject based on the depth map;

harvesting from the virtual skeleton by the computer a set of subject metrics corresponding to distances between predetermined points of the virtual skeleton;

providing the subject metrics as input to an engine of the computer configured to output a virtual body mesh as a function of the subject metrics;

refining the virtual body mesh by the computer by varying the subject metrics to decrease distance between points on the depth map and corresponding points of the virtual body mesh, the refined virtual body mesh being a basis for a posable, three-dimensional, virtual avatar resembling the subject;

invoking a selection engine of the computing system, the selection engine being configured to select the first article from an inventory of articles for sale to the subject based on one or more of color, style, and brand matching with respect to a wearable second article already in a wardrobe of the subject;

obtaining at the computer data that identifies the selected first article, the data including a plurality of article metrics at least partly defining the first article;

sizing by the computer a virtualized form of the first article to fit the subject;

attaching by the computer virtualized forms of the first and second articles to the avatar;

providing the avatar, with the virtualized forms of the first and second articles attached, from the computer to a display component for the subject to review; and

providing by the computer a mechanism for the subject to buy the first article.

20. A computing system comprising:

a depth camera;

a computer operatively coupled to the depth camera, the computer including;

a processor; and

a computer memory holding instructions that when executed by the processor, cause the processor to;

receive from the depth camera a depth map of the subject;

obtain a virtual skeleton of the subject based on the depth map;

harvest from the virtual skeleton a set of subject metrics corresponding to distances between predetermined points of the virtual skeleton;

provide the subject metrics as input to an engine to output a virtual body mesh as a function of the subject metrics;

refine the virtual body mesh by varying the subject metrics to decrease distance between points on the depth map and corresponding points of the virtual body mesh, the refined virtual body meshing being a basis for a posable, three-dimensional, virtual avatar resembling the subject;

obtain data that identifies the wearable article as being selected for the subject, the data including a plurality of article metrics that at least partly define the wearable article;

attach a virtualized form of the wearable article to the avatar; and

provide the avatar, with the virtualized form of the wearable article attached, to a display component for the subject to review.