Personalized stylized-avatar generation technique (granted).
The present disclosure is related to a method to generate user representative avatars that fit within a design paradigm. The method includes receiving depth information corresponding to multiple user features of the user, determining one or more feature landmarks for the user based on the depth information, utilizing the one or more feature landmarks to classify a first user feature relative to an avatar feature category, selecting a first avatar feature from the avatar feature category based on the classification of the first user feature, combining the first avatar feature within an avatar representation to generate a user avatar, and output the user avatar for display.
FIELD (1) The present disclosure relates generally to generating avatars or other user representations for media, interactive content, and other applications. BACKGROUND (2) Avatars or other graphic representations of users, characters, or objects are used in many applications, such as video games, interactive content, images, electronic communication (e.g., texting), instant messaging, and the like. Often, it is desirable to include individualized features on an avatar that allow a user to more closely resemble the avatar and allow others to identify a particular avatar as corresponding to a user, e.g., have a user's likeness. Additionally, in many instances, there is a desire to have avatars that match within a particular “style” or design framework (e.g., match character design elements). (3) Current avatar generation systems do not balance the competing factors of user likeness with design paradigms and select one factor over the other. For example, many video games will allow a user to vary certain colors of a character, but these colors are previously stored options and while may happen to match the user are not selected so as to match the user. In other examples, the avatars may be generated within a design paradigm, but do not resemble the user. In many instances, avatars need to be “manually” created, with a user actively selecting the particular avatar features that the user wishes to include on their own avatar, which is time consuming and often leads to inaccurate
1. A method to generate avatars representative of a user and a character design language, comprising: analyzing one or more images of a user to determine user characteristics, wherein the user characteristics comprise depth information and color information from a user face; determining measurements for a plurality of facial features of the user face based on at least a portion of the user characteristics, comprising: generating a user mesh based on the user depth information; wrapping the user mesh with a generic mesh to generate a wrapped mesh, wherein the wrapping is based on an alignment of one or more facial landmarks of the user mesh with one or more generic facial landmarks of the generic mesh, wherein the one or more landmarks of the user mesh are determined by the user landmark information; and subtracting the generic mesh from the wrapped mesh to output an avatar mesh, wherein the avatar mesh corresponds to the avatar facial shape to be used for the avatar; classifying a first facial feature of the plurality of facial features relative to a first class of avatar facial features corresponding to the character design language based on the measurements of the first facial features and the color information; selecting a first avatar facial feature from the first class of avatar facial features based on the classification; classifying a second facial feature of the plurality of facial features relative to a second class of avatar facial features corresponding to the character design language based on the measurements of the second facial features and the color information; selecting a second avatar facial feature from the second class of avatar facial features based on the classification; and generating an avatar representative of the user and the character design language by applying the first avatar facial feature and the second avatar facial feature to an avatar. ||
9. A system for generating a unique avatar representation of a user comprising: a camera for capturing at least one image of the user; and a computer in electronic communication with the camera, comprising: a non-transitory memory component for storing a plurality of avatar facial features; and a processor in electronic communication with the memory and configured to perform the following operations: determine user characteristics from the at least one image, wherein the user characteristics comprise depth information and color information for a plurality of facial features of the user; determine user landmark information from the user characteristics; generate a user mesh based on the user depth information; wrap the user mesh with a generic mesh to generate a wrapped mesh, wherein the wrapping is based on an alignment of one or more facial landmarks of the user mesh with one or more generic facial landmarks of the generic mesh, wherein the one or more landmarks of the user mesh are determined by the user landmark information; subtract the generic mesh from the wrapped mesh to output an avatar mesh, wherein the avatar mesh corresponds to the avatar facial shape to be used for the avatar; select a first avatar feature from a plurality of first avatar features based on a best fit analysis of a first facial feature of the user to the plurality of first avatar features; select a second avatar feature from a plurality of second avatar features based on a best fit analysis of a second facial feature of the user to the plurality of second avatar features; and generate an avatar representative of a likeness of the user that includes the first avatar feature and the second avatar feature.