Recovering Articulated Object Models from 3D Range Data
This addresses the challenge of modeling complex articulated objects for robotics or computer vision applications, but it is incremental as it builds on existing non-rigid registration techniques.
The paper tackles the problem of unsupervised learning of articulated object models from 3D range data, resulting in an algorithm that automatically recovers part decompositions and skeletons, demonstrated by recovering a 15-part model from 7 configurations and a 4-part model with non-rigid deformation.
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 allthe 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 large number of object parts while avoiding local maxima. We demonstrate the algorithm on real world datasets, recovering a 15-part articulated model of a human puppet from just 7 different puppet configurations, as well as a 4 part model of a fiexing arm where significant non-rigid deformation was present.