Automatic 3D Modeling

Abstract

An automatic 3D modeling system and method are described in which a 3D model may be generated from a picture or another image. For example, a 3D model for a face of a person may be automatically generated. The system and method also permits gestures/behaviors associated with a 3D model to automatically generated so that the gestures/behaviors may be applied to any 3D models.

1 . (canceled) 
     
     
         2 . A method comprising:
 determining a first variable indicating a first change of a surface of a first object represented in an image, and a second variable indicating a second change of a vertex associated with the first object; and   animating the second object based on the first and second variables.   
     
     
         3 . The method of  claim 2 , wherein:
 the first variable comprises a two dimensional variable indicating the first change of the surface of the first object; and   the second variable comprises a three dimensional variable indicating the second change of the vertex associated with the first object.   
     
     
         4 . The method of  claim 2 , further comprising:
 animating the second object by applying a model comprising the two dimensional variable and the three dimensional variable to the second object.   
     
     
         5 . The method of  claim 4 , wherein the model further comprises a third variable indicating a third change in a coloration occurring during a movement of the first object. 
     
     
         6 . The method of  claim 2 , further comprising:
 determining a scalar field variable representing a mapping between a feature space of a movement of the first object and a model space to enable transformation of the vertex.   
     
     
         7 . The method of  claim 6 , wherein the scalar field variable comprises an array having respective entries for a plurality of vertices, the entries comprising respective three-dimensional vectors configured to store data representing changes in scale of the plurality of vertices in the feature space. 
     
     
         8 . The method of  claim 7 , wherein the scalar field variable is based on a weighted interpolation of respective positions of the vertex mapped to a second space associated with a polygon in the feature space. 
     
     
         9 . The method of  claim 6 , further comprising:
 generating the model, wherein generating the model includes generating the feature space and mapping the movement between the feature space and the model space.   
     
     
         10 . A non-transitory computer readable medium having computer instructions stored thereon, the instructions comprising:
 determining a first variable indicating a first change of a surface of a first object represented in an image, and a second variable indicating a second change of a vertex associated with the first object; and   animating the second object based on the first and second variables.   
     
     
         11 . The non-transitory computer readable medium of  claim 10 , wherein:
 the first variable comprises a two dimensional variable indicating the first change of the surface of the first object; and   the second variable comprises a three dimensional variable indicating the second change of the vertex associated with the first object.   
     
     
         12 . The non-transitory computer readable medium of  claim 10 , the instructions further comprising:
 animating the second object by applying a model comprising the two dimensional variable and the three dimensional variable to the second object.   
     
     
         13 . The non-transitory computer readable medium of  claim 12 , wherein the model further comprises a third variable indicating a third change in a coloration occurring during a movement of the first object. 
     
     
         14 . The non-transitory computer readable medium of  claim 12 , the instructions further comprising:
 determining a scalar field variable representing a mapping between a feature space of a movement of the first object and a model space to enable transformation of the vertex.   
     
     
         15 . The non-transitory computer readable medium of  claim 14 , wherein the scalar field variable comprises an array having respective entries for a plurality of vertices, the entries comprising respective three-dimensional vectors configured to store data representing changes in scale of the plurality of vertices in the feature space. 
     
     
         16 . The non-transitory computer readable medium of  claim 15 , wherein the scalar field variable is based on a weighted interpolation of respective positions of the vertex mapped to a second space associated with a polygon in the feature space. 
     
     
         17 . The non-transitory computer readable medium of  claim 14 , further comprising:
 generating the model, wherein generating the model includes generating the feature space and mapping the movement between the feature space and the model space.   
     
     
         18 . An apparatus comprising:
 means for determining a first variable indicating a first change of a surface of a first object represented in an image, and a second variable indicating a second change of a vertex associated with the first object; and   means for animating the second object based on the first and second variables.   
     
     
         19 . The apparatus of  claim 18 , wherein:
 the first variable comprises a two dimensional variable indicating the first change of the surface of the first object; and   the second variable comprises a three dimensional variable indicating the second change of the vertex associated with the first object.   
     
     
         20 . The apparatus of  claim 18 , further comprising:
 means for animating the second object by applying a model comprising the two dimensional variable and the three dimensional variable to the second object.