Automated image augmentation using a virtual character

1. An image processing system comprising:

a computing platform including a hardware processor and a system memory;

the system memory storing an image augmentation software code, a three-dimensional (3D) poses library including a plurality of poses, and a 3D body shapes library including a plurality of body shapes;

a two-dimensional (2D) pose estimation software having computing instructions;

the hardware processor configured to execute the image augmentation software code to:

obtain an image including a real-world environment image portion corresponding to a real-world environment, a marker image portion corresponding to a marker in the real-world environment, and a human image portion corresponding to a human in the real-world environment;

provide at least one portion of the image including the human image portion as an input to the 2D pose estimation software;

receive from the 2D pose estimation software, a 2D pose data generated based on the at least one portion of the image including the human image portion;

identify a 3D pose and a 3D body shape corresponding to the at least one portion of the image including the human image portion, using the 2D pose data, the plurality of poses in the 3D poses library and the plurality of body shapes in the 3D body shapes library, wherein the 3D pose is initialized to fit inside a bounding box of the marker; and

generate a virtual character having the identified 3D pose and the identified 3D body shape.

2. The image processing system of claim 1 , wherein the hardware processor is further configured to execute the image augmentation software code to:

display, on a display, an augmented reality image including the human and the virtual character within the real-world environment.

3. The image processing system of claim 1 , wherein the computing platform is part of a communication device remote from the 2D pose estimation software, the computing platform further comprising a camera, and wherein the hardware processor is further configured to execute the image augmentation software code to obtain the image using the camera.

4. The image processing system of claim 1 , wherein the hardware processor is further configured to execute the image augmentation software code to:

display, on a display, an augmented reality image in which the human appears beside the virtual character in the real-world environment, and wherein the virtual character appears as a copy of the human who is wearing a suit or a costume.

5. The image processing system of claim 1 , wherein the image is a RGB image.

6. The image processing system of claim 2 , wherein a time lapse between receiving the image by the image augmentation software code and displaying the augmented reality image on the display is less than five seconds.

7. The image processing system of claim 2 , wherein the hardware processor is further configured to execute the image augmentation software code to:

utilize the 3D body shape to generate a shadow cast from the human to the virtual character in the augmented reality image.

8. The image processing system of claim 2 , wherein the virtual character and the human are non-overlapping in the augmented reality image.

9. The image processing system of claim 2 , wherein the virtual character at least partially overlaps the human in the augmented reality image.

10. The image processing system of claim 2 , wherein the hardware processor is further configured to execute the image augmentation software code to:

utilize the 3D body shape to generate a partial occlusion of the virtual character by the human in the augmented reality image.

11. A method for use by an image processing system including a computing platform having a hardware processor and a system memory storing an image augmentation software code, a three-dimensional (3D) poses library including a plurality of poses, and a 3D body shapes library including a plurality of body shapes, the method comprising:

obtaining, by the image augmentation software code executed by the hardware processor, an image including a real-world environment image portion corresponding to a real-world environment, a marker image portion corresponding to a marker in the real-world environment, and a human image portion corresponding to a human in the real-world environment;

providing, by the image augmentation software code executed by the hardware processor, at least one portion of the image including the human image portion as an input to the 2D pose estimation software;

receiving from the 2D pose estimation software, by the image augmentation software code executed by the hardware processor, a 2D pose data generated based on the at least one portion of the image including the human image portion;

identifying, by the image augmentation software code executed by the hardware processor, a 3D pose and a 3D body shape corresponding to the at least one portion of the image including the human image portion, using the 2D pose data, the plurality of poses in the 3D poses library and the plurality of body shapes in the 3D body shapes library, wherein the 3D pose is initialized to fit inside a bounding box of the marker; and

generating, by the image augmentation software code executed by the hardware processor, a virtual character having the identified 3D pose and the identified 3D body shape.

12. The method of claim 11 , further comprising:

displaying, on a display, an augmented reality image including the human and the virtual character within the real-world environment.

13. The method of claim 11 , wherein the computing platform is part of a communication device remote from the 2D pose estimation software, the computing platform further comprising a camera, the method further comprising:

obtaining, by the image augmentation software code executed by the hardware processor, the image using the camera.

14. The method of claim 11 , further comprising:

displaying, on a display, an augmented reality image in which the human appears beside the virtual character, and wherein, in the augmented reality image, the virtual character appears as a copy of the human who is wearing a suit or a costume.

15. The method of claim 12 , wherein a time lapse between receiving the image by the image augmentation software code and displaying the augmented reality image on the display is less than five seconds.

16. The method of claim 12 , further comprising:

utilizing the 3D body shape to generate a shadow cast from the human to the virtual character in the augmented reality image.

17. The method of claim 12 , wherein the virtual character at least partially overlaps the human in the augmented reality image.

18. The method of claim 12 , further comprising:

utilizing the 3D body shape to generate a partial occlusion of the virtual character by the human in the augmented reality image.

19. The image processing system of claim 1 , wherein the computing platform further includes a camera configured to obtain the image, and wherein the hardware processor is further configured to execute the image augmentation software code to:

estimate, using the marker image portion of the image, an orientation and a position of the camera.

20. The method of claim 11 , wherein the computing platform further includes a camera configured to obtain the image, and wherein the method further comprises:

estimating, using the marker image portion of the image, an orientation and a position of the camera.