摘要 |
A method of generating a 3D representation of a subject, such as a body shape of a human, comprises comparing a depth image of the subject with a plurality of representative images, wherein each representative image is associated with a respective parametric model such as a cluster model including a shape, pose models that include variables that can be made to fit a depth image of the subject,; identifying a representative image from the plurality of images that closest matches to the depth image of the subject; and generating a 3-D representation of the subject by fitting the selected parametric model to the depth image of the subject. Representative images may be alpha, silhouettes or depth images. |