Timezone: »

From Deformations to Parts: Motion-based Segmentation of 3D Objects
Soumya Ghosh · Erik Sudderth · Matthew Loper · Michael J Black

Tue Dec 04 07:00 PM -- 12:00 AM (PST) @ Harrah’s Special Events Center 2nd Floor #None

We develop a method for discovering the parts of an articulated object from aligned meshes capturing various three-dimensional (3D) poses. We adapt the distance dependent Chinese restaurant process (ddCRP) to allow nonparametric discovery of a potentially unbounded number of parts, while simultaneously guaranteeing a spatially connected segmentation. To allow analysis of datasets in which object instances have varying shapes, we model part variability across poses via affine transformations. By placing a matrix normal-inverse-Wishart prior on these affine transformations, we develop a ddCRP Gibbs sampler which tractably marginalizes over transformation uncertainty. Analyzing a dataset of humans captured in dozens of poses, we infer parts which provide quantitatively better motion predictions than conventional clustering methods.

Author Information

Soumya Ghosh (IBM Research)
Erik Sudderth (Brown University)
Matthew Loper (Max Planck Institute for Intelligent Systems)
Michael J Black (Max Planck Institute for Intelligent Systems)

More from the Same Authors