- Number
- 11315298
- Published
- 2022-04-26
- Filed
- 2019-03-25
- Assignee
- DISNEY ENTERPRISES, INC.
- Inventors
- Comploi; Dumene, Gonzalez; Francisco E.
- CPC
- G06T19/20; G06V40/172; G06T13/40; G06T7/50; G06T17/20
- Verdict
- Low Notable software
- Source
- Google Patents · FreePatentsOnline
The keeper's note
Personalized stylized-avatar generation technique.
Abstract
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.
Background
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
Claims
1. A method to generate individualized user-character avatars representative of a user's likeness and a character design framework associated with character design language, the method comprising: receiving by a processor depth information corresponding to multiple user features of a user, wherein the multiple user features correspond to anatomical features of the 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 facial hair user feature by a facial hair category relative to an avatar facial hair feature category, the utilizing comprising: generating by the processor a user mesh representing a three dimensional shape for at least the facial hair feature, wrapping by the processor the user mesh with a generic mesh to generate a wrapped mesh, and comparing the wrapped mesh representing the facial hair feature with a plurality of facial hair avatar features in the avatar facial hair feature category; selecting, by the processor from an avatar feature database, a facial hair avatar feature from the plurality of facial hair avatar features in the avatar facial hair feature category based on the classification and comparison of the facial hair user feature such that the facial hair avatar feature is a facial hair avatar feature out of the plurality of facial hair avatar features that most closely matches the facial hair user feature, and wherein the facial hair avatar feature corresponds to the character design framework associated with the character design language, and wherein the facial hair avatar feature comprises a subtype; combining by the processor the facial hair avatar feature with an avatar representation to generate an individualized user-character avatar representative of both the user's likeness and the character design framework associated with the character design language; and outputting by the processor the individualized user-character avatar to a display. ||
6. The method claim 5, wherein the second user feature corresponds to a hair line, an eye brow shape, a nose shape, a hair texture, or an eye brow texture. ||
8. A system for generating individualized user-character avatars representative of a person's likeness and a character design framework associated with character design language, the system 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 by a first category, a first type, a first subtype, or combinations thereof, relative to a first graphical feature category and a second facial feature, relative to a second graphical feature category, wherein the classified first facial feature is a first anatomical feature of the person corresponding to a facial hair characteristic of the person and the classified second facial feature is a second anatomical feature of the person different from the facial hair characteristic, and wherein the utilizing comprises: generating a person mesh representing a three dimensional shape representation of the person's face, including at least the first facial feature and the second facial feature, wrapping a generic mesh over the person mesh to generate a wrapped mesh, and comparing the wrapped mesh representing the first facial feature and the second facial feature with a plurality of facial hair graphical features in the first graphical feature category and a plurality of facial hair graphical features in the second graphical feature category; select, from an avatar feature database, a first graphical feature from the plurality of facial hair graphical features in the first graphical feature category based on the classification and comparison, wherein the first graphical feature is a graphical feature from the plurality of facial hair graphical features that most closely matches the first facial feature; select, from the avatar feature database a second graphical feature from the plurality of graphical features corresponding to the second anatomical feature in the second graphical feature category based on the classification, wherein the second graphical feature is a graphical feature from the plurality of graphical features that most closely matches the second facial feature, and wherein the first facial feature and second facial feature correspond to the character design framework associated with the character design language, and wherein the first graphical feature and the second graphical feature comprises a subtype; and combine the first graphical feature and the second graphical feature together to generate an individualized user-character avatar representative of both the person's likeness and the character design framework associated with the character design language. ||
13. A method to generate individualized user-character avatars representative of a user's likeness and a character design framework associated with character design language, the method comprising: receiving by a processor depth information corresponding to a facial feature of the user, wherein the facial feature corresponds to a facial hair feature of the user; detecting by analyzing the depth information by the processor, a location of the facial feature; quantizing by the processor the facial feature, by a category, a type, a subtype, or combinations thereof, into a respective avatar facial feature type, the quantizing comprising: generating a user mesh corresponding to a three dimensional shape representation of the user's face, wrapping a generic mesh over the user mesh to generate a wrapped mesh, and comparing the wrapped mesh representing the user's face with a plurality avatar facial hair elements; selecting, from an avatar feature database, avatar facial hair elements from the plurality of avatar facial hair elements to an individualized user-character avatar based on the respective facial feature type and the depth information, wherein the selected avatar facial hair elements are those from the plurality of avatar facial hair elements that most closely match facial feature of the user and correspond to the character design framework associated with the character design language; generating the individualized user-character avatar by the processor by combining the avatar facial elements together, wherein the individualized user-character is representative of both the user's likeness and the character design framework associated with the character design language; and outputting by the processor to a display the individualized user-character avatar for display.