Group-valued regularization for motion segmentation of articulated shapes

Guy Rosman, Michael M. Bronstein, Alexander M. Bronstein, Alon Wolf, Ron Kimmel

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Motion-based segmentation is an important tool for the analysis of articulated shapes. As such, it plays an important role in mechanical engineering, computer graphics, and computer vision. In this chapter, we study motion-based segmentation of 3D articulated shapes. We formulate motion-based surface segmentation as a piecewise-smooth regularization problem for the transformations between several poses. Using Lie-group representation for the transformation at each surface point, we obtain a simple regularized fitting problem. An Ambrosio-Tortorelli scheme of a generalized Mumford-Shah model gives us the segmentation functional without assuming prior knowledge on the number of parts or even the articulated nature of the object. Experiments on several standard datasets compare the results of the proposed method to state-of-the-art algorithms.

Original languageEnglish
Title of host publicationMathematics and Visualization
EditorsMichael BreuB, Petros Maragos, Alfred Bruckstein
PublisherSpringer Heidelberg
Number of pages19
ISBN (Electronic)9783642341410
ISBN (Print)9783319912738, 9783540250326, 9783540250760, 9783540332749, 9783540886051, 9783642150135, 9783642216077, 9783642231742, 9783642273421, 9783642341403, 9783642341403, 9783642543005
StatePublished - 2013
Externally publishedYes
EventDagstuhl Workshop on Innovations for Shape Analysis: Models and Algorithms, 2011 - Dagstuhl, Germany
Duration: 3 Apr 20118 Apr 2011

Publication series

NameMathematics and Visualization
ISSN (Print)1612-3786
ISSN (Electronic)2197-666X


ConferenceDagstuhl Workshop on Innovations for Shape Analysis: Models and Algorithms, 2011


Dive into the research topics of 'Group-valued regularization for motion segmentation of articulated shapes'. Together they form a unique fingerprint.

Cite this