3d video performance segmentation

We present a novel approach that achieves segmentation of subject body parts in 3D videos. 3D video consists in a free-viewpoint video of real-world subjects in motion immersed in a virtual world. Each 3D video frame is composed of one or several 3D models. A topology dictionary is used to cluster 3D video sequences with respect to the model topology and shape. The topology is characterized using Reeb graph-based descriptors and no prior explicit model on the subject shape is necessary to perform the clustering process. In this frame-work, the dictionary consists in a set of training input poses with a priori segmentation and labels. As a consequence, all identified frames of 3D video sequences can be automatically segmented. Finally, motion flows computed between consec-utive frames are used to transfer segmented region labels to unidentified frames. Our method allows us to perform robust body part segmentation and tracking in 3D cinema sequences. Index Terms — 3D video, topology dictionary, shape matching, body segmentation 1