Recovering Articulated Object Models from 3D Range Data (2004)by D. Anguelov, H.C. Pang, D. Koller, P. Srinivasan, and S. Thrun
Abstract:
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 di erent object instances, and the articulated object skeleton linking the parts. Our algorithm first registers all the meshes using an unsupervised nonrigid 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 15part articulated model of a human puppet from just 7 different puppet con gurations, as well as a 4 part model of a existing arm where significant nonrigid deformation was present.
Download Information
D. Anguelov, H.C. Pang, D. Koller, P. Srinivasan, and S. Thrun (2004). "Recovering Articulated Object Models from 3D Range Data." Proceedings of the Twentieth Conference on Uncertainty in AI (UAI) (pp. 1826).


Bibtex citation
@inproceedings{Anguelov+al:UAI04,
author = {D. Anguelov and H.C. Pang and D. Koller and P. Srinivasan and S. Thrun},
title = {Recovering Articulated Object Models from 3D Range Data},
booktitle = {Proceedings of the Twentieth Conference on Uncertainty in AI (UAI)},
year = 2004,
pages = {1826},
}
full list
