ML-generated personalized stylized avatars.
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
The present disclosure relates generally to generating avatars or other user representations for media, interactive content, and other applications.BACKGROUND
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).
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 inacc
1. A method to generate individualized user avatars representative of a user's likeness and a character design framework comprising: receiving by a processor depth information corresponding to multiple user features of a user; determining by the processor one or more feature landmarks for the user based on the depth information; utilizing by the processor the one or more feature landmarks to classify a first user feature relative to an avatar feature category; selecting by the processor a first avatar feature from a plurality of avatar features in the avatar feature category based on the classification of the first user feature, wherein the first avatar feature corresponds to the first user feature, and wherein the first avatar feature corresponds to the character design framework; combining by the processor the first avatar feature with an avatar representation to generate an individualized user avatar, wherein the individualized user avatar is representative of both the user's likeness and the character design framework; and outputting by the processor the individualized user avatar to a display.
9. A system for generating individualized user avatars representative of a person's likeness and a character design framework comprising: a camera for capturing images of a person; and a computer in electronic communication with the camera, comprising: a non-transitory memory component for storing a plurality of graphical features; and a processor in electronic communication with the memory and configured to perform the following operations: receive the captured images of the person; determine from the captured images a plurality of facial landmarks for the person; utilize the plurality of facial landmarks to classify a first facial feature relative to a first graphical feature category and a second facial feature relative to a second graphical feature category; select a first graphical feature from a plurality of graphical features in the first graphical feature category and a second graphical feature from a plurality of graphical features in the second graphical feature category based on the classification, wherein the first graphical feature corresponds to the first facial feature and the second graphical feature corresponds to the second facial feature, and wherein the first facial feature and second facial feature correspond to the character design framework; and combine the first graphical feature and the second graphical feature together to generate an individualized user avatar representative of both the person's likeness and the character design framework.
15. A method to generate individualized user avatars comprising: receiving by a processor depth information corresponding to multiple facial features of a user; detecting by analyzing the depth information by the processor, locations of the multiple facial features; quantizing by the processor the facial features into a respective avatar facial feature type; selecting avatar facial elements from a plurality of avatar facial elements to represent an individualized user avatar based on the respective facial feature type and the depth information, wherein the selected avatar facial elements correspond to facial features of the user and correspond to a character design framework; and generating the individualized user avatar by the processor by combining the avatar facial elements together, wherein the individualized user avatar is representative of both a user's likeness and the character design framework; and outputting by the processor to a display the individualized user avatar for display.