Automatic Registration for Articulated Shapes

Automatic Registration for Articulated Shapes
Will Chang	Matthias Zwicker
University of California, San Diego
Computer Graphics Forum (Proceedings of SGP 2008) Copenhagen, Denmark, July 2 - 4, 2008

Registration for an arm dataset pair. The source mesh (a) is aligned to the target mesh (b). The hand region is missing a significant amount of data in both meshes, but after alignment the surface of the hand is completed nicely (c). The assigned labels are shown in (d) for the source (bottom) and the target (top), and corresponding parts have the same label assignment. Also, the segmentation naturally corresponds to the different parts of the arm.
Abstract We present an unsupervised algorithm for aligning a pair of shapes in the presence of significant articulated motion and missing data, while assuming no knowledge of a template, user-placed markers, segmentation, or the skeletal structure of the shape. We explicitly sample the motion, which gives a priori the set of possible rigid transformations between parts of the shapes. This transforms the problem into a discrete labeling problem, where the goal is to find an optimal assignment of transformations for aligning the shapes. We then apply graph cuts to optimize a novel cost function, which encodes a preference for a consistent motion assignment from both source to target and target to source. We demonstrate the robustness of our method by aligning several synthetic and real-world datasets. Downloads Paper [ Paper ] (16.3 MB Adobe PDF, Hi-Res) [ BibTex ] Talk Slides [ Slides ] (15.7 MB Powerpoint Presentation)