Novel Skeletal Representation for

Articulated Creatures

by Gabriel J. Brostow, Irfan Essa, Drew Steedly, and Vivek Kwatra



Contact: Gabriel J. Brostow,



Volumetric structures are frequently used as shape descriptors for 3D data. The capture of such data is being facilitated by developments
in multi-view video and range scanning, extending to subjects that are alive and moving. In this paper, we examine vision-based modeling
and the related representation of moving articulated creatures using spines. We define a spine as a branching axial structure representing
the shape and topology of a 3D objectís limbs, and capturing the limbsícorrespondence and motion over time.


Our spine concept builds on skeletal representations often used to describe the internal structure of an articulated object and the significant
protrusions. The algorithms for determining both 2D and 3D skeletons generally use an objective function tuned to balance stability against

the responsiveness to detail. Our representation of a spine provides for enhancements over a 3D skeleton, afforded by temporal robustness

and correspondence. We also introduce a probabilistic framework that is needed to compute the spine from a sequence of surface data.


We present a practical implementation that approximates the spineís joint probability function to reconstruct spines for synthetic and real
subjects that move.



Gabriel J. Brostow, Irfan Essa, Drew Steedly, and Vivek Kwatra

"Novel Skeletal Representation For Articulated Creatures"

ECCV, May 2004, Vol III: 66-78.

Official version © Springer-Verlag

ECCV 2004.pdf  (5Mb)    BibTex


Gabriel J. Brostow

"Novel Skeletal Representation For Articulated Creatures"

Ph.D. Thesis, Georgia Institute of Technology, 2004.

PDF (21Mb)     BibTex



Movie in MPEG 1 format (94Mb)

Movie-small version (16Mb)

Picture of data-catpure stage (800Kb)




New Subjects

(these datasets are not yet processed)