Composite avatar

Abstract

Examples are disclosed that relate to generating an avatar of a user that accurately represents an identity of the user. In one example, a manually-generated avatar (218) including a first head connected (300) to a body (302) is received. Image data (208) of a user is received from a camera (206). A machine-generated avatar (226) of the user is generated, via an avatar machine-learning model (224), based at least on the image data (208). The avatar machine-learning model (224) is trained on training data including a plurality of three-dimensional scans of human heads. The machine-generated avatar (226) of the user comprises a second head (310) having facial features that map to actual facial features of the user. A composite avatar (236) of the user is generated by replacing the first head (300) with the second head (310) on the body (302) of the manually-generated avatar (218). A graphical user interface (238) including the composite avatar (236) is displayed via a display device (240).

Images