Systems and methods of generating augmented reality (AR) objects

1. An apparatus for generating one or more Augmented Reality (AR) objects, comprising:

memory;

an image capturing module including an image sensor, the image capturing module configured to capture, based on instructions from an application executed on the apparatus, a digital image of at least a portion of a real-world scene including a human face; and

one or more processors coupled to the memory and the image capturing module, the one or more processors configured to:

detect the at least a portion of the human face in the digital image;

segment the digital image into one or more areas corresponding to the at least a portion of the human face;

estimate one or more lighting conditions in the real-world scene based on the digital image;

generate, using data from the digital image in the one or more areas corresponding to the at least a portion of a human face and the estimated one or more lighting conditions, an augmented reality (AR) object representing the at least a portion of a human face, wherein the AR object is an editable version of the at least a portion of a human face and is divided into a plurality of editable parts;

display a first output image, the first output image depicting the real-world scene and the AR object, wherein the AR object is associated with a physical object in the real-world scene in the first output image;

edit the AR object based on a user input, wherein editing the AR object includes manipulating one or more parts of the plurality of editable parts associated with at least one of the plurality of editable parts; and

display a second output image, the second output image depicting the real-world scene and the edited AR object, wherein the AR object is associated with the physical object in the real-world scene in the second output image.

2. The apparatus of claim 1 , wherein segmenting the digital image comprises subtracting a background from the digital image.

3. The apparatus of claim 1 , wherein the at least a portion of a human face is depicted in a two-dimensional sketch.

4. The apparatus of claim 1 , wherein the at least a portion of a human face comprises a three-dimensional object.

5. The apparatus of claim 1 , wherein the one or more processors are configured to:

segment the digital image into one or more areas corresponding to a background, wherein the background is a tracking area.

6. The apparatus of claim 1 , wherein the user input includes a gesture determined based on one or more images.

7. The apparatus of claim 6 , wherein the gesture is determined based on depth data associated with the one or more images.

8. The apparatus of claim 7 , wherein the processor is further configured to:

edit a geometry of the AR object in response to a second user input; and

display the AR object, including the edited geometry, in a third output image, wherein the AR object is associated with the physical object in the real-world scene in the third output image.

9. The apparatus of claim 8 , wherein the second user input includes a touch input.

10. The apparatus of claim 7 , wherein the 3D gesture is a hand gesture.

11. The apparatus of claim 7 , wherein

editing the AR object includes adding a depth effect to at least one part of the AR object, the added depth effect causing the at least one part to appear to have more than two dimensions when displayed.

12. The apparatus of claim 11 , wherein the added depth effect causes the at least one part to appear to have two and a half dimensions.

13. The apparatus of claim 11 , wherein an amount of the depth effect added to the at least one part of the AR object is based on a determined finger pressure on a display.

14. The apparatus of claim 6 , wherein the AR object is based on a facial expression of the human.

15. The apparatus of claim 1 , wherein the AR object represents a surface reflectance associated with the at least a portion of the human face based on the estimated one or more lighting conditions.

16. The apparatus of claim 1 , wherein the one or more processors are configured to:

display, on a display, the AR object in real-time.

17. The apparatus of claim 1 , wherein the AR object is generated in real-time by the apparatus without using an electronic device other than the apparatus.

18. The apparatus of claim 1 , wherein the apparatus includes a display for displaying the first and second output images.

19. The apparatus of claim 1 , wherein editing the AR object animating includes adding sounds to the AR object.

20. A method for generating one or more augmented reality (AR) objects by a device, the method comprising:

capturing, by a camera of the device based on instructions from an application executed on the device, a digital image of at least a portion of a real-world scene including a human face;

detecting the at least a portion of the human face in the digital image;

segmenting the digital image into one or more areas corresponding to the at least a portion of the human face;

estimating one or more lighting conditions in the real-world scene based on the digital image;

generating, using data from the digital image in the one or more areas corresponding to the at least a portion of a human face and the estimated one or more lighting conditions an augmented reality (AR) object representing the at least a portion of a human face, wherein the AR object is an editable version of the at least a portion of a human face and is divided into a plurality of editable parts;

displaying a first output image, the first output image depicting the real-world scene and the AR object, wherein the AR object is associated with a physical object in the real-world scene in the first output image;

editing the AR object based on a user input, wherein editing the AR object includes manipulating one or more parts of the plurality of editable parts associated with at least one of the plurality of editable parts; and

displaying a second output image, the second output image depicting the real-world scene and the edited AR object, wherein the AR object is associated with the physical object in the real-world scene in the second output image.

21. The method of claim 20 , wherein segmenting the digital image comprises subtracting a background from the digital image.

22. The method of claim 20 , wherein the at least a portion of a human face is depicted in a two-dimensional sketch.

23. The method of claim 20 , wherein the at least a portion of a human face comprises a three-dimensional object.

24. The method of claim 20 , further comprising:

segmenting the digital image into one or more areas corresponding to a background, wherein the background is a tracking area.

25. The method of claim 20 , wherein the user input includes a gesture determined based on one or more images.

26. The method of claim 25 , wherein the gesture is determined based on depth data associated with the one or more images.

27. The method of claim 26 , further comprising:

editing a geometry of the AR object in response to a second user input; and

displaying the AR object, including the edited geometry, in a third output image, wherein the AR object is associated with the physical object in the real-world scene in the third output image.

28. The method of claim 27 , wherein the second user input includes a touch input.

29. The method of claim 26 , wherein the 3D gesture is a hand gesture.

30. The method of claim 26 , wherein editing the AR object includes adding a depth effect to at least one part of the AR object, the added depth effect causing the at least one part to appear to have more than two dimensions when displayed.

31. The method of claim 30 , wherein the added depth effect causes the at least one part to appear to have two and a half dimensions.

32. The method of claim 30 , wherein an amount of the depth effect added to the at least one part of the AR object is based on a determined finger pressure on a display of the device.

33. The method of claim 25 , wherein the AR object is based on a facial expression of the human.

34. The method of claim 20 , wherein the AR object represents a surface reflectance associated with the at least a portion of the human face based on the estimated one or more lighting conditions.

35. The method of claim 20 , further comprising:

displaying, on a display of the device, the AR object in real-time.

36. The method of claim 20 , wherein the two-dimensional AR object is generated in real-time by the device without using an electronic device other than the device.

37. The method of claim 20 , wherein editing the AR object animating includes adding sounds to the AR object.

38. A non-transitory computer readable storage medium storing instructions that when executed cause one or more processor of a device to:

capture, by a camera of the device based on instructions from an application executed on the device, a digital image of at least a portion of a real-world scene including a human face;

detect the at least a portion of the human face in the digital image;

segment the digital image into one or more areas corresponding to the at least a portion of the human face;

estimate one or more lighting conditions in the real-world scene based on the digital image;

generate, using data from the digital image in the one or more areas corresponding to the at least a portion of a human face and the estimated one or more lighting conditions, an augmented reality (AR) object representing the at least a portion of a human face, wherein the AR object is an editable version of the at least a portion of a human face and is divided into a plurality of editable parts;

display a first output image, the first output image depicting the real-world scene and the AR object, wherein the AR object is associated with a physical object in the real-world scene in the first output image;

edit the AR object based on a user input, wherein editing the AR object includes manipulating one or more parts of the plurality of editable parts associated with at least one of the plurality of editable parts; and

display a second output image, the second output image depicting the real-world scene and the edited AR object, wherein the AR object is associated with the physical object in the real-world scene in the second output image.