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 for generating a three dimensional model of an animated object from an image, the method comprising:
determining the boundary of the animated object to be modeled;
determining the location of one or more landmarks on the animated object to be modeled;
aligning the image of the animated object with the landmarks with a deformation grid;
generating a 3D deformable model of the animated object based on the mapping of the image of the object to the deformation grid; and
defining a gesture stored in a feature space which is mapped to the 3D deformable model wherein the gesture can be applied to a three dimensional model of another object.
2. The method of claim 1 , wherein the boundary determining further comprises statistically directed linear integration of a field of pixels whose values differ based on the presence of an object or the presence of a background.
3. The method of claim 1 , wherein the boundary determining further comprises performing a statistically directed seed fill operation in order to remove the background around the image of the object.
4. The method of claim 3 , wherein determining the landmarks further comprises identifying features found by procedural correlation or band pass filtering and thresholding in statistically characteristic zones as determined during the boundary determination.
5. The method of claim 4 , wherein determining the landmarks further comprises determining additional landmarks based on a refinement of the boundary areas.
6. The method of claim 5 , wherein determining the landmarks further comprises adjusting the landmarks by the user.
7. A computer-implemented system for generating a three dimensional model of an animated object from an image, the computer implemented system comprising:
a three dimensional model generation module farther comprising instructions that receive an image of an object and instructions that automatically generate a three dimensional model of the object; and
wherein the instructions that automatically generate a three dimensional model of the object further comprising instructions that determine a boundary of the animated object to be modeled, instructions that determine the location of one or more landmarks on the animated object to be modeled, instructions that align the image of the animated object with the landmarks with a deformation grid, instructions that generate a 3D model of the animated object based on the mapping of the image of the animated object to the deformation grid and instructions that define a gesture stored in a feature space which is mapped to the 3D deformable model wherein the gesture can be applied to a three dimensional model of another object.
8. The system of claim 7 , wherein the instructions that determine the boundary further comprises instructions that perform statistically directed linear integration of a field of pixels whose values differ based on the presence of an object or the presence of a background.
9. The system of claim 7 , wherein the instructions that determine the boundary farther comprises instructions that perform a statistically directed seed fill operation in order to remove the background around the image of the object.
10. The system of claim 9 , wherein instructions that determine the landmarks further comprises instructions that identify features found by procedural correlation or band pass filtering and thresholding in statistically characteristic zones as determined during the boundary determination.
11. The system of claim 10 , wherein instructions that determine the landmarks further comprises instructions that determine additional landmarks based on a refinement of the boundary areas.
12. The system of claim 11 , wherein instructions that determine the landmarks farther comprises instructions that adjust the landmarks by the user.