Automatic 3D modeling system and method
View Patent ↗An automatic 3D modeling system and method are described in which a 3D model may be generated from a picture or other 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. A method comprising:
receiving, by a computing device, an image of a first object performing a gesture, the first object having a surface and a vertex;
defining, by the computing device, a gesture object comprising a two dimensional variable configured to indicate a change associated with the surface in response to the gesture and a three dimensional variable configured to indicate a change associated with the vertex in response to the gesture; and
applying, by the computing device, the gesture object to a model of a second object to animate the second object.
2. The method of claim 1 , wherein the gesture object further comprises:
a scalar field variable configured to store a mapping between a feature space of the gesture and a model space of a second model to enable transformation of the vertex.
3. The method of claim 2 , wherein the gesture object further comprises:
a texture change variable configured to store changes in coloration of the second model during the gesture.
4. The method of claim 2 , wherein the scalar field variable comprises an array having respective entries for vertices of the gesture, the entries comprising respective three-dimensional vectors configured to store data representing changes in scale of the vertices in the feature space between an undeformed state and a deformed state.
5. The method of claim 4 , wherein the scalar field variable is based on a weighted interpolation of respective positions of the vertex mapped to a space associated with a polygon in the feature space.
6. The method of claim 4 , further comprising automatically generating the gesture object, wherein generating the gesture object includes generating the feature space and mapping the gesture between the feature space and the model space.
7. A non-transitory computer-readable medium having instructions stored thereon, the instructions comprising:
instructions for receiving an image of a first object performing a gesture, the first object having a surface and a vertex;
instructions for defining a gesture object comprising a two dimensional variable configured to indicate a change associated with the surface in response to the gesture and a three dimensional variable configured to indicate a change associated with the vertex in response to the gesture; and
instructions for applying the gesture object to a model of a second object to animate the second object.
8. The non-transitory computer-readable medium of claim 7 , wherein the gesture object further comprises:
a scalar field variable configured to store a mapping between a feature space of the gesture and a model space of a second model to enable transformation of the vertex.
9. The non-transitory computer-readable medium of claim 8 , wherein the gesture object further comprises:
a texture change variable configured to store changes in coloration of the second model during the gesture.
10. The non-transitory computer-readable medium of claim 8 , wherein the scalar field variable comprises an array having respective entries for vertices of the gesture, the entries comprising respective three-dimensional vectors configured to store data representing changes in scale of the vertices in the feature space between an undeformed state and a deformed state.
11. The non-transitory computer-readable medium of claim 10 , wherein the scalar field variable is based on a weighted interpolation of respective positions of the vertex mapped to a space associated with a polygon in the feature space.
12. The non-transitory computer-readable medium of claim 10 , the instructions further comprising:
instructions for automatically generating the gesture object, wherein generating the gesture object includes generating the feature space and mapping the gesture between the feature space and the model space.
13. An apparatus comprising:
means for receiving an image of a first object performing a gesture, the first object having a surface and a vertex;
means for defining a gesture object comprising a two dimensional variable configured to indicate a change associated with the surface in response to the gesture and a three dimensional variable configured to indicate a change associated with the vertex in response to the gesture; and
means for applying the gesture object to a model of a second object to animate the second object.
14. The apparatus of claim 13 , wherein the gesture object further comprises:
a scalar field variable configured to store a mapping between a feature space of the gesture and a model space of a second model to enable transformation of the vertex.
15. The apparatus of claim 14 , wherein the gesture object further comprises:
a texture change variable configured to store changes in coloration of the second model during the gesture.
16. The apparatus of claim 14 , wherein the scalar field variable comprises an array having respective entries for vertices of the gesture, the entries comprising respective three-dimensional vectors configured to store data representing changes in scale of the vertices in the feature space between an undeformed state and a deformed state.
17. The apparatus of claim 16 , wherein the scalar field variable is based on a weighted interpolation of respective positions of the vertex mapped to a space associated with a polygon in the feature space.
18. The apparatus of claim 16 , further comprising:
means for automatically generating the gesture object, wherein generating the gesture object includes generating the feature space and mapping the gesture between the feature space and the model space.