Recovering Articulated Object Models from 3D Range Data

We address the problem of unsupervised learning of complex articulated object models from 3D range data. We describe an algorithm whose input is a set of meshes corresponding to different configurations of an articulated object. The algorithm automatically recovers a decomposition of the object into approximately rigid parts, the location of the parts in the different object instances, and the articulated object skeleton linking the parts. Our algorithm first registers all the meshes using an unsupervised non-rigid technique described in a companion paper. It then segments the meshes using a graphical model that captures the spatial contiguity of parts. The segmentation is done using the EM algorithm, iterating between finding a decomposition of the object into rigid parts, and finding the location of the parts in the object instances. Although the graphical model is densely connected, the object decomposition step can be performed optimally and efficiently, allowing us to identify a ...

• Type: Conference
• Year: 2004
• Where: UAI
• Authors: Dragomir Anguelov, Daphne Koller, Hoi-Cheung Pang, Praveen Srinivasan, Sebastian Thrun
• Keywords: Articulated Object, Complex Articulated Object, Object Instances, UAI 2004, UAI 2008