Producing three-dimensional representation based on images of a person

1. A method, comprising:

receiving, by a processing device, a first polygonal mesh representing a human body part, wherein the first polygonal mesh is compliant with a target application topology;

receiving a second polygonal mesh representing the human body part, wherein the second polygonal mesh is derived from a plurality of images of a person;

detecting an anatomical feature within an image of the plurality of images;

projecting, using a camera transformation matrix, the detected anatomical feature onto the second polygonal mesh; and

aligning the first polygonal mesh and the second polygonal mesh in view of a position of the anatomical feature.

2. The method of claim 1 , further comprising:

receiving the plurality of images from a mobile computing device.

3. The method of claim 1 , further comprising:

receiving the plurality of images from a specialized computing device equipped with a still image camera and a light source, wherein a lens of the still image camera and the light source are equipped with cross-polarizing filters.

4. The method of claim 1 , wherein the part of the human body comprises a head.

5. The method of claim 1 , wherein optimizing the value of the metric comprises performing a simulating annealing method.

6. The method of claim 1 , wherein optimizing the value of the metric comprises performing an iterative closest point method.

7. The method of claim 1 , wherein modifying the first polygonal mesh comprises modifying at least one of: a position of a polygonal face of the first polygonal mesh or an orientation of a polygonal face of the first polygonal mesh.

8. The method of claim 1 , further comprising:

producing a camera transformation matrix defining at least one of: a position of a camera relative to an object being imaged, an orientation of the camera, or a scale an image produced by the camera.

9. The method of claim 1 , further comprising: generating an edge-finding image by analyzing a luminance gradient to detect a position of a first curvature corresponding to the anatomical feature.

10. The method of claim 1 , further comprising:

producing a texture by mapping a plurality of image pixels to a surface defined by the first polygonal mesh.

11. The method of claim 10 , wherein the texture comprises at least one of: a light map, a shaded color map, a color map, a normal map, a half bent normal map, or an occlusion map.

12. The method of claim 10 , further comprising:

analyzing one or more images of the plurality of images to determine a skin tone to be applied to the texture.

13. The method of claim 10 , further comprising:

determining a skin tone to be applied to the texture.

14. The method of claim 10 , further comprising:

producing at least one of a first file comprising a representation of the first polygonal mesh and a second file comprising a representation of the texture.

15. The method of claim 14 , further comprising:

providing at least one of the first file and the second file for editing by an artist user.

16. A computer-readable non-transitory storage medium comprising executable instructions to cause a processing device to:

receive, by the processing device, a first polygonal mesh representing a human body part, wherein the first polygonal mesh is compliant with a target application topology;

receive a second polygonal mesh representing the human body part, wherein the second polygonal mesh is derived from a plurality of images of a person;

detect an anatomical feature within an image of the plurality of images;

project, using a camera transformation matrix, the detected anatomical feature onto the second polygonal mesh; and

align the first polygonal mesh and the second polygonal mesh in view of a position of the anatomical feature.