We present a novel approach to reliable and efficient recovery of part-descriptions in terms of superquadric models from range data. We show that superquadrics can directly be recovered from unsegmented data, thus avoiding any presegmentation steps (e.g., in terms of surfaces). The approach is based on the recover-andselect paradigm [10] . We present several experiments on real and synthetic range images, where we demonstrate the stability of the results with respect to viewpoint and noise.

more »

... x Terms-Range image segmentation, recover-and-select paradigm, recovery of volumetric models, superquadrics. --------3 -------- SUPERQUADRIC MODELS The criteria for the selection of geometric primitives have been studied extensively by vision researchers (see [3] and the references therein). These criteria not only constrain the choice of the primitives, but impose certain conditions on the model-recovery procedure as well. However, all model-based approaches are restricted, since they cannot model everything possibly present in 0162-8828/97/$10.00 © 1997 IEEE ¥¥¥¥¥¥¥¥¥¥¥¥¥¥¥¥ • The authors are with the acceptance by P. Flynn. For information on obtaining reprints of this article, please send e-mail to: tpami@computer.org, and reference IEEECS Log Number 105705.