| CPC G06T 13/40 (2013.01) | 20 Claims |

|
1. A processor-implemented method, comprising:
defining a mapping function for mapping points from a source space to respectively corresponding points of a target space, based on feature points of the source space where an object in motion is positioned and based on feature points of the target space where the motion of the object is represented, the source space and the target space having a same number of dimensions;
using the mapping function to map a root position point of the object in the source space to a corresponding target root position point in the target space;
using the mapping function to map a source direction of the object in the source space to a corresponding target direction of the object in the target space;
using the mapping function to map a main joint point of the object in the source space to a corresponding target main joint point of the object in the target space;
determining a target sub-joint point in the target space, the determining based on the target main joint point and based on joint information of the object that interrelates joints of the object in the source space, wherein the target sub-joint is not the target main joint and is determined based on a relation to the target main joint indicated by the joint information;
generating data representing motion of the object in the target space by modifying a pose of the object in the target space to match the target main joint; and
displaying an animation according to the data representing the motion of the object.
|