VIRTUALIZING CONTENT

• US 20150363977A1
• Filed: 06/16/2015
• Published: 12/17/2015
• Est. Priority Date: 10/31/2012
• Status: Active Grant

• Current Assignee: Outward, Inc. (Williams-Sonoma Inc.)
• Original Assignee: Outward, Inc. (Williams-Sonoma Inc.)
• Inventors: Chui, Clarence, Mignard, Marc
• Granted Patent: US 10,210,658 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06T 11/00 2D [Two Dimensional] image generation
• CPC Class Codes: G06T 19/006 Mixed reality object pose determination, tracking or camera calibration for mixed reality G06T7/00
• CPC Class Codes: G06V 20/64 Three-dimensional objects
• CPC Class Codes: H04N 21/234318 by decomposing into objects, e.g. MPEG-4 objects
• CPC Class Codes: H04N 21/4223 Cameras H04N23/00 takes precedence
• CPC Class Codes: H04N 21/8126 involving additional data, e.g. news, sports, stocks, weather forecasts
• CPC Class Codes: H04N 23/80 Camera processing pipelines; Components thereof
• CPC Class Codes: H04N 7/0125 one of the standards being a high definition standard

Abstract

Techniques for virtualizing content are disclosed. One or more objects comprising source video content are determined. The one or more objects comprising the source video content are virtualized by mapping each to and representing each with a corresponding database object. Data comprising the corresponding database objects is provided for rendering the source video content instead of any original pixel information of the source video content so that a virtualized version of the source video content is rendered.

Claims

1. A method, comprising:

identifying objects in camera captured source content;

mapping each identified object to a corresponding existing database object including by mapping a prescribed number of non-coplanar points of each identified object to corresponding points of the corresponding existing database object; and

virtualizing the source content by representing the source content completely using existing database objects to which the identified objects are mapped;

wherein the virtualized version of the source content comprises a re-imagined version of the source content that does not include any original camera captured pixel information.

2. The method of claim 1, further comprising determining camera pose with respect to the source content and providing the same camera pose with respect to the virtualized version of the source content.

3. The method of claim 1, wherein identifying objects is at least in part automated, at least is in part assisted by human intervention, or both.

4. The method of claim 1, wherein mapping is at least in part automated, at least in part assisted by human intervention, or both.

5. The method of claim 1, wherein mapping comprises selecting an existing database object that best matches an identified object.

6. The method of claim 1, wherein mapping comprises purposely selecting a mismatching existing database object for an identified object.

7. The method of claim 1, wherein mapping comprises mapping an identified object that comprises a partial object to a whole or complete existing database object.

8. The method of claim 1, further comprising tracking and mapping motion of an identified object to motion of the corresponding existing database object in the virtualized version of the source content.

9. The method of claim 1, wherein the source content is two-dimensional and the virtualized version of the source content is three-dimensional.

10. The method of claim 1, wherein the source content comprises source video content.

11. A system, comprising:

a processor configured to;

identify objects in camera captured source content;

map each identified object to a corresponding existing database object including by mapping a prescribed number of non-coplanar points of each identified object to corresponding points of the corresponding existing database object; and

virtualize the source content by representing the source content completely using existing database objects to which the identified objects are mapped, wherein the virtualized version of the source content comprises a re-imagined version of the source content that does not include any original camera captured pixel information; and

a memory coupled to the processor and configured to provide the processor with instructions.

12. The system of claim 11, wherein the processor is further configured to determine camera is pose with respect to the source content and provide the same camera pose with respect to the virtualized version of the source content.

13. The system of claim 11, wherein the processor is further configured to receive human input for identifying objects, mapping objects, or both.

14. The system of claim 11, wherein to map comprises to select an existing database object that best matches an identified object.

15. The system of claim 11, wherein to map comprises to purposely select a mismatching existing database object for an identified object.

16. The system of claim 11, wherein to map comprises to map an identified object that comprises a partial object to a whole or complete existing database object.

17. The system of claim 11, wherein the processor if further configured to track and map motion of an identified object to motion of the corresponding existing database object in the virtualized version of the source content.

18. The system of claim 11, wherein the source content is two-dimensional and the virtualized version of the source content is three-dimensional.

19. The system of claim 11, wherein the source content comprises source video content.

20. A computer program product embodied in a non-transitory computer usable storage medium, comprising computer instructions for:

identifying objects in camera captured source content;

mapping each identified object to a corresponding existing database object including by mapping a prescribed number of non-coplanar points of each identified object to corresponding points of the corresponding existing database object; and

virtualizing the source content by representing the source content completely using existing database objects to which the identified objects are mapped;

wherein the virtualized version of the source content comprises a re-imagined version of the source content that does not include any original camera captured pixel information.