Method for providing a three dimensional body model
A method for providing a three-dimensional body model which may be applied for an animation, based on a moving body, wherein the method comprises providing a parametric three-dimensional body model, which allows shape and pose variations; applying a standard set of body markers; optimizing the set of body markers by generating an additional set of body markers and applying the same for providing 3D coordinate marker signals for capturing shape and pose of the body and dynamics of soft tissue; and automatically providing an animation by processing the 3D coordinate marker signals in order to provide a personalized three-dimensional body model, based on estimated shape and an estimated pose of the body by means of predicted marker locations.
1. A method for providing a three-dimensional body model which may be applied for an animation, based on a moving body, wherein the method comprises:
providing a parametric three-dimensional body model, which allows shape and pose variations;
applying a set of body markers;
optimizing the set of body markers by generating an additional set of body markers and applying the additional set of body markers to the three dimensional body model for providing 3D coordinate marker signals for capturing shape and pose of the body and dynamics of soft tissue;
automatically providing an animation by processing the 3D coordinate marker signals in order to provide a personalized three-dimensional body model, based on estimated shape and an estimated pose of the body by means of predicted marker locations; and
the three-dimensional body model is trained by means of a set of scans in a plurality of shapes and poses in order to represent shape and pose-dependent deformations.
2. The method according to claim 1 , wherein the marker set is sparse.
3. The method according to claim 1 , wherein a handful of markers is arranged on any body part.
4. The method according to claim 1 , wherein the number of body markers is below or equal to 47 or 67.
5. The method according to claim 1 , wherein the pose of the body is assumed to vary smoothly over time.
6. The method according to claim 1 , wherein the body shape of the subject does not change over time.
7. The method according to claim 1 , wherein the body shape of the subject changes over time.
8. The method according to claim 6 , wherein the changing body shape is constrained to be close to a fixed body shape representing a person's identity.
9. The method according to claim 1 , wherein the method is applied for providing an animation of a character without converting motion capture data to a rigged model of the character.
10. The method according to claim 1 , wherein the three-dimensional body model is directly used for an animation of a character.
11. The method according to claim 1 , wherein the three-dimensional body model is used as reference for retargeting the data to other animated characters.
12. The method according to claim 1 , wherein the three-dimensional body model considers dynamics of complex surface deformation, in particular of soft tissue, like fat and muscle.
13. The method according to claim 12 , wherein the dynamics of complex surface deformation is transferred to a further three-dimensional body model.
14. A method according to claim 13 , wherein the dynamics of complex surface deformation is exaggerated or attenuated, when transferring it to the further three-dimensional body model.
15. The method according to claim 1 , wherein the method may be executed on archival motion capture sequences.
16. The method according to claim 1 , wherein the additional set of body markers is positioned on soft tissue.
17. The method according to claim 1 , wherein the additional set of body markers is selected from a generated superset of additional maker sets.
18. The method according to 17 , wherein the additional set of body markers is selected to optimize a given objective function.
19. The method according to 17 , wherein a greedy search method is used for selecting the additional set of body markers.
20. The method according to claim 1 , wherein the method is used in a motion capture system.
21. The method according to claim 1 , wherein body is a human or animal body.
22. Non-transitory computer readable medium containing computer-readable instructions stored therein for causing a computer processor to perform the steps of the method according to claim 1 .
23. An apparatus for providing a three-dimensional body model which may be applied for an animation, based on a moving body, comprising:
a model storage which is adapted for providing a parametric three-dimensional body model, which allows shape and pose variations;
a position detector which is adapted for applying a set of body markers to the three dimensional body model;
an optimizer, which is adapted for optimizing the set of body markers by generating an additional set of body markers and applying the additional set of body markers to the three dimensional body model for providing 3D coordinate marker signals for capturing shape and pose of the body and dynamics of soft tissue;
a processor for automatically processing the 3D coordinate marker signals in order to provide a personalized three-dimensional body model, based on estimated shape and an estimated pose of the body by means of predicted marker locations; and training the three-dimensional body by means of a set of scans in a plurality of shapes and poses in order to represent shape and pose-dependent deformations, and in particular, wherein the training is executed separately for men and women.