Post-split contralateral combinations

A non-transitory computer-readable medium storing a computer program for performing a method, the computer-readable medium comprising:

• program instructions for generating a first sub-shape of a first shape that corresponds to a first expression of a face, wherein the first sub-shape corresponds to a first portion of the face;
• program instructions for generating a second sub-shape of a second shape that corresponds to a second expression of the face, wherein the second sub-shape corresponds to a second portion of the face;
• modifying the first sub-shape;
• program instructions for generating a combined shape by combining the first sub-shape that is modified and the second sub-shape using an editing application;
• and
• program instructions for applying a correction to the combined shape to align relative portions of the combined shape with the first shape or the second shape, wherein the correction is at least partially identified using an artificial intelligence (AI) model that takes inputs from the first sub-shape that is modified and the second sub-shape.

A computer system comprising:

• a processor;
• memory coupled to the processor and having stored therein instructions that, if executed by the computer system, cause the computer system to execute a method, comprising:
• generating a first sub-shape of a first shape that corresponds to a first expression of a face, wherein the first sub-shape corresponds to a first portion of the face;
• program instructions for generating a second sub-shape of a second shape that corresponds to a second expression of the face, wherein the second sub-shape corresponds to a second portion of the face;
• program instructions for modifying the first sub-shape;
• program instructions for generating a combined shape by combining the first sub-shape that is modified and the second sub-shape using an editing application;
• and
• program instructions for applying a correction to the combined shape to align relative portions of the combined shape with the first shape or the second shape, wherein the correction is at least partially identified using an artificial intelligence (AI) model that takes inputs from the first sub-shape that is modified and the second sub-shape.