Methods and systems to modify a two dimensional facial image to increase dimensional depth and generate a facial image that appears three dimensional
AssigneeActivision Publishing, Inc.
InventorsPaul D. Yan, Thitikun Vorachart
Life of this patent
Estimating the term…
Abstract
The specification describes methods and systems for increasing a dimensional depth of a two-dimensional image of a face to yield a face image that appears three dimensional. The methods and systems identify key points on the 2-D image, obtain a texture map for the 2-D image, determines one or more proportions within the 2-D image, and adjusts the texture map of the 3-D model based on the determined one or more proportions within the 2-D image.
Claims23
A computer-implemented method for generating a facial image that appears three dimensional from a two-dimensional facial image, the method being implemented in at least one computer having a processor and a random access memory, the method comprising:
- acquiring the two-dimensional facial image from a storage unit;
- using the at least one computer, generating a texture map of the two-dimensional facial image;
- using the at least one computer, projecting the texture map of the two-dimensional facial image onto a three-dimensional mesh image;
- using the at least one computer, determining a first set of one or more positional relationships between anatomical features in the two-dimensional facial image;
- using the at least one computer, determining a second set of one or more positional relationships between anatomical features in the three-dimensional mesh image;
- using the at least one computer, determining a plurality of scaling factors, wherein each of said scaling factors is a function of at least one of the first set of one or more positional relationships and at least one of the second set of one or more positional relationships;
- using the at least one computer, adjusting the three-dimensional mesh image based on the determined plurality of scaling factors to yield the facial image that appears three dimensional;
- and
- using the at least one computer, outputting the facial image that appears three dimensional.
A computer readable non-transitory medium comprising a plurality of executable programmatic instructions wherein, when said plurality of executable programmatic instructions are executed by a processor, a process for generating a facial image that appears three dimensional from a two-dimensional facial image is executed, the plurality of executable programmatic instructions comprising:
- programmatic instructions, stored in the computer readable non-transitory medium, for acquiring the two-dimensional facial image from a storage unit;
- programmatic instructions, stored in the computer readable non-transitory medium, for generating a texture map of the two-dimensional facial image;
- programmatic instructions, stored in the computer readable non-transitory medium, for translating the texture map of the two-dimensional facial image onto a three-dimensional mesh image;
- programmatic instructions, stored in the computer readable non-transitory medium, for determining a first set of one or more positional relationships between anatomical features in the two-dimensional facial image;
- programmatic instructions, stored in the computer readable non-transitory medium, for determining a second set of one or more positional relationships between anatomical features in the three-dimensional mesh image;
- programmatic instructions, stored in the computer readable non-transitory medium, for determining a plurality of scaling factors, wherein each of said scaling factors is a function of at least one of the first set of one or more positional relationships and at least one of the second set of one or more positional relationships;
- programmatic instructions, stored in the computer readable non-transitory medium, for adjusting the three-dimensional mesh image based on the determined plurality of scaling factors to yield the facial image that appears three dimensional;
- and
- programmatic instructions, stored in the computer readable non-transitory medium, for outputting the facial image that appears three dimensional.
Dependencies are inferred from the claim text.