Template Matching Skeletonization Based on Gauss Sphere Representation

Abstract

Skeletonization, or automatic skeleton extraction, is a technology in 3DCG which automatically extract skeletons (i.e. bones, joints and their hierarchical structures) from 3D models. Such skeletons are important shape and pose descriptors for object representation, object recognition etc. Some existing skeletonization methods have difficulties in correctly extracting the position of joints. Some other methods are able to extract joints correctly to some extent, but controlling the number of bones and joints in their structure is not allowed. Therefore applying motion data acquired from motion capture devices to 3D models still involves a lot of manual work. In this paper, we propose a novel animation skeletonization method suited for CG animation based on Gauss sphere representation. By applying vertex Gauss sphere representation first and then applying template matching approach regardless of the object's shape, the proposed method is able to extract the same numbers of joints or bones in the same structure as in given motion data, i.e. one can directly apply existing motion data without the need of manual adjustment. Experimental results showed that the proposed method achieves 90% accuracy of pose estimation and 73% accuracy of joint estimation.