Systems and methods for performing virtual application of makeup effects based on a source image

A system, comprising:

• a memory storing instructions;
• a processor coupled to the memory and configured by the instructions to at least:
• obtain a source image depicting a facial region having one or more makeup effects;
• perform facial alignment and define a plurality of source regions having the one or more makeup effects, the source regions corresponding to facial features in the source image;
• for each source region, extract attributes of the one or more makeup effects;
• identify a closest matching feature template for each source region based on the attributes, wherein one of the attributes comprises a shape of the source region, and wherein identifying the closest matching feature template for each source region based on the attributes comprises:
• defining the shape of the source region based on a maximum IoU (Intersection of Union) metric, wherein the IoU metric is calculated based on an area of overlap and an area of union, and wherein the maximum IoU comprises the largest area of overlap;
• and
• identifying the closest matching feature template for each source region based on a feature template having a closest matching shape;
• obtain a digital image of a facial region of a user;
• perform facial alignment and identify a plurality of target regions corresponding to the plurality of source regions;
• and
• apply a matching feature template of a corresponding source region to each of the target regions.

A non-transitory computer-readable storage medium storing instructions to be implemented by a computing device having a processor, wherein the instructions, when executed by the processor, cause the computing device to at least:

• obtain a source image depicting a facial region having one or more makeup effects;
• perform facial alignment and define a plurality of source regions having the one or more makeup effects, the source regions corresponding to facial features in the source image;
• for each source region, extract attributes of the one or more makeup effects;
• identify a closest matching feature template for each source region based on the attributes, wherein one of the attributes comprises a shape of the source region, and wherein identifying the closest matching feature template for each source region based on the attributes comprises:
• defining the shape of the source region based on a maximum IoU (Intersection of Union) metric, wherein the IoU metric is calculated based on an area of overlap and an area of union, and wherein the maximum IoU comprises the largest area of overlap;
• and
• identifying the closest matching feature template for each source region based on a feature template having a closest matching shape;
• obtain a digital image of a facial region of a user;
• perform facial alignment and identify a plurality of target regions corresponding to the plurality of source regions;
• and
• apply a matching feature template of a corresponding source region to each of the target regions.