Generation of avatar reflecting player appearance

Abstract

Systems, methods, and computer media for generating an avatar reflecting a player's current appearance. Data describing the player's current appearance is received. The data includes a visible spectrum image of the player, a depth image including both the player and a current background, and skeletal data for the player. The skeletal data indicates an outline of the player's skeleton. Based at least in part on the received data, one or more of the following are captured: a facial appearance of the player; a hair appearance of the player; a clothing appearance of the player; and a skin color of the player. A 3 D avatar resembling the player is generated by combining the captured facial appearance, hair appearance, clothing appearance, and/or skin color with predetermined avatar features.

Having thus described the invention, what is claimed is: 
     
         1 . A system for generating an avatar reflecting a user's current appearance comprising:
 a data acquisition component configured to generate data corresponding to the user's current appearance, wherein the data includes a visible spectrum image of the user, a depth image associated with the user and a background, and skeletal data indicating an outline of the user's skeleton;   a face capture component that receives the data and generate a face texture map comprising a plurality of face alignment points by:
 identifying a head portion of the visible spectrum image corresponding to the user's head and face using the skeletal data; 
 identifying facial features in the identified head portion; 
 determining face alignment points corresponding to identified facial features; and 
 mapping face alignment points corresponding to identified facial features to associated destination points of a template texture map; and 
   an avatar generation component that generates the avatar using the face texture map.   
     
     
         2 . The system of  claim 1 , further comprising:
 a clothing capture component that captures an appearance of the user's clothing, wherein the appearance of the user's clothing comprises an outer clothing boundary identified using the depth image and at least one inner clothing boundary identified using the visible spectrum image.   
     
     
         3 . The system of  claim 2 , wherein the clothing capture component also:
 identifies areas of the visible spectrum image of the user corresponding to an arm, a leg, or a combination thereof using the skeletal data; and   analyzes identified areas of the visible spectrum image using either color classification or gradient analysis to detect one or more of: a shirt sleeve, a pants leg, a shorts leg, a skirt hem, a dress hem, or a combination thereof.   
     
     
         4 . The system of  claim 3 , wherein the clothing capture component also:
 identifies areas of the depth image of the user corresponding to the user's legs using the skeletal data; and   analyzes between the identified areas of the depth image to detect either a skirt hem or a dress hem by:
 distinguishing a background depth from a user depth; and 
 identifying a substantially horizontal edge separating the background depth from the user depth. 
   
     
     
         5 . The system of  claim 1 , further comprising:
 a hair capture component that captures attributes of the user's hair appearance, in part, by identifying an extent of the user's hair and matches the captured attributes to a predetermined hairstyle template.   
     
     
         6 . One or more computer storage devices storing computer-useable instructions that, when used by one or more computing devices, cause the one or more computing devices to perform a method for generating an avatar reflecting a user's current appearance, the method comprising:
 receiving data corresponding to the user's current appearance, wherein the data includes a visible spectrum image of the user, a depth image associated with the user and a background, and skeletal data indicating an outline of the user's skeleton;   identifying a head portion of the visible spectrum image corresponding to the user's head using the skeletal data;   identifying a face portion within the head portion corresponding to the user's face and facial features within the face portion;   determining face alignment points corresponding to identified facial features;   mapping face alignment points to corresponding destination points of a template texture map;   capturing a plurality of hairstyle attributes, in part, by identifying an extent of the user's hair;   matching the identified extent of the user's hair to a predetermined hairstyle template; and   generating the avatar using the face texture map and the captured plurality of hairstyle attributes.   
     
     
         7 . The one or more computer storage devices of  claim 6 , wherein the face portion is identified by comparing the head portion to a database of known faces using machine learning techniques. 
     
     
         8 . The one or more computer storage devices of  claim 6 , wherein the extent of the user's hair comprises an outer hair boundary identified using the depth image. 
     
     
         9 . The one or more computer storage devices of  claim 6 , wherein the extent of the user's hair comprises an inner hair boundary identified by analyzing the visible spectrum image. 
     
     
         10 . The one or more computer storage devices of  claim 9 , wherein the inner hair boundary is identified, in part, using depth-informed background removal. 
     
     
         11 . The one or more computer storage devices of  claim 9 , wherein the method further comprises estimating the user's forehead location within the face portion by sampling a central face color wherein the inner hair boundary is identified, in part, using the estimated forehead location. 
     
     
         12 . The one or more computer storage devices of  claim 6 , wherein capturing the plurality of hairstyle attributes further comprises segmenting the user's hair from the visible spectrum image using depth-informed background removal, forehead estimation, face removal, or a combination thereof. 
     
     
         13 . The one or more computer storage devices of  claim 6 , wherein the captured plurality of hairstyle attributes comprise the identified extent of the user's hair and one or more aspects of the user's hair including: bangs, an amount of hair on top, an amount of hair on each side, an amount beyond the user's chin, forehead coverage, or a combination thereof, and wherein a combination of the captured plurality of hairstyle attributes are matched to at least one predetermined hairstyle template. 
     
     
         14 . The one or more computer storage devices of  claim 6 , wherein the method further comprises identifying the user's hair color using the visible spectrum image, wherein the identified hair color is applied to the predetermined hairstyle template. 
     
     
         15 . A computerized method comprising for generating an avatar reflecting a user's current appearance, the method comprising:
 receiving data corresponding to the user's current appearance, wherein the data includes a visible spectrum image of the user, a depth image associated with the user and a background, and skeletal data indicating an outline of the user's skeleton;   identifying a head portion of the visible spectrum image corresponding to the user's head using the skeletal data;   identifying a face portion within the head portion corresponding to the user's face and facial features within the face portion;   determining face alignment points corresponding to identified facial features;   calculating sizes of a plurality of facial features using the determined face alignment points;   determining morph configurations for each of the plurality of facial features using the calculated sizes;   combining a plurality of predetermined three-dimensional (3D) head models based upon the determined morph configurations;   mapping face alignment points corresponding to identified facial features to associated destination points of the morphed 3-D head model; and   generating the avatar using the morphed 3-D head model.   
     
     
         16 . The computerized method of  claim 15 , further comprising:
 capturing a plurality of hairstyle attributes, in part, by identifying an extent of the user's hair.   
     
     
         17 . The computerized method of  claim 16 , wherein identifying the extent of the user's hair comprises identifying an outer hair boundary using the depth image and an inner hair boundary by analyzing the visible spectrum image. 
     
     
         18 . The computerized method of  claim 15 , further comprising:
 capturing an appearance of the user's clothing, wherein the appearance of the user's clothing comprises an outer clothing boundary identified using the depth image and at least one inner clothing boundary identified using the visible spectrum image.   
     
     
         19 . The computerized method of  claim 18 , wherein capturing the appearance of the user's clothing further comprises:
 identifying areas of the visible spectrum image of the user corresponding to an arm, a leg, or a combination thereof using the skeletal data; and   analyzing the identified areas of the visible spectrum image using either color classification or gradient analysis to detect one or more of: a shirt sleeve, a pants leg, a shorts leg, a skirt hem, a dress hem, or a combination thereof.   
     
     
         20 . The computerized method of  claim 18 , wherein capturing the appearance of the user's clothing further comprises:
 identifying areas of the depth image of the user corresponding to the user's legs using the skeletal data; and   analyzing between the identified areas of the depth image to detect either a skirt hem or a dress hem by:
 distinguishing a background depth from a user depth; and 
 identifying a substantially horizontal edge separating the background depth from the user depth.