Body model composition update from two-dimensional face images

A computing system, comprising:

• one or more processors;
• and
• a memory storing program instructions that when executed by the one or more processors cause the one or more processors to at least:
• receive a two-dimensional (“2D”) face image of a face of a body;
• process the 2D face image to determine a first face-based body feature corresponding to a first existing body feature stored for the body;
• determine at least one of a difference or a ratio between the first face-based body feature and the first existing body feature;
• generate, based at least in part on the first face-based body feature and the first existing body feature, an updated first body feature for the body;
• generate, based at least in part on one or more of the difference or the ratio and a second existing body feature stored for the body, an updated second body feature for the body;
• and
• provide at least the updated first body feature and the updated second body feature.

A method, comprising:

• generating a plurality of face-based body features for a body corresponding to a face represented in a two-dimensional (“2D”) face image, wherein:
• the body is not represented in the 2D face image;
• and
• at least one of the plurality of face-based body features corresponds to an existing body feature of the body that was previously determined for the body;
• determining at least one of a difference or a ratio between the at least one of the plurality of face-based body features and the existing body feature to which it corresponds;
• updating, based at least in part on the face-based body features, the existing body feature of the body to generate an updated first body feature;
• updating, based at least in part on one or more of the difference or the ratio, a second existing body feature of the body to generate an updated second body feature;
• and
• presenting, at least the updated first body feature and the updated second body feature.