Group-valued regularization framework for motion segmentation of dynamic non-rigid shapes
Rosman G, Bronstein MM, Bronstein AM, Wolf A, Kimmel R. 2012. Group-valued regularization framework for motion segmentation of dynamic non-rigid shapes. 3rd International Conference on Scale Space and Variational Methods in Computer Vision. SSVM: Scale Space and Variational Methods in Computer Vision, LNCS, vol. 6667, 725–736.
Download
No fulltext has been uploaded. References only!
Conference Paper
| Published
| English
Scopus indexed
Author
Rosman, Guy;
Bronstein, Michael M.;
Bronstein, Alex M.ISTA 
;
Wolf, Alon;
Kimmel, Ron
;
Wolf, Alon;
Kimmel, RonSeries Title
LNCS
Abstract
Understanding of articulated shape motion plays an important role in many applications in the mechanical engineering, movie industry, graphics, and vision communities. In this paper, we study motion-based segmentation of articulated 3D shapes into rigid parts. We pose the problem as finding a group-valued map between the shapes describing the motion, forcing it to favor piecewise rigid motions. Our computation follows the spirit of the Ambrosio-Tortorelli scheme for Mumford-Shah segmentation, with a diffusion component suited for the group nature of the motion model. Experimental results demonstrate the effectiveness of the proposed method in non-rigid motion segmentation.
Publishing Year
Date Published
2012-01-09
Proceedings Title
3rd International Conference on Scale Space and Variational Methods in Computer Vision
Publisher
Springer Nature
Volume
6667
Page
725-736
Conference
SSVM: Scale Space and Variational Methods in Computer Vision
Conference Location
Ein-Gedi, Israel
Conference Date
2011-05-29 – 2011-06-02
ISBN
ISSN
eISSN
IST-REx-ID
Cite this
Rosman G, Bronstein MM, Bronstein AM, Wolf A, Kimmel R. Group-valued regularization framework for motion segmentation of dynamic non-rigid shapes. In: 3rd International Conference on Scale Space and Variational Methods in Computer Vision. Vol 6667. Springer Nature; 2012:725-736. doi:10.1007/978-3-642-24785-9_61
Rosman, G., Bronstein, M. M., Bronstein, A. M., Wolf, A., & Kimmel, R. (2012). Group-valued regularization framework for motion segmentation of dynamic non-rigid shapes. In 3rd International Conference on Scale Space and Variational Methods in Computer Vision (Vol. 6667, pp. 725–736). Ein-Gedi, Israel: Springer Nature. https://doi.org/10.1007/978-3-642-24785-9_61
Rosman, Guy, Michael M. Bronstein, Alex M. Bronstein, Alon Wolf, and Ron Kimmel. “Group-Valued Regularization Framework for Motion Segmentation of Dynamic Non-Rigid Shapes.” In 3rd International Conference on Scale Space and Variational Methods in Computer Vision, 6667:725–36. Springer Nature, 2012. https://doi.org/10.1007/978-3-642-24785-9_61.
G. Rosman, M. M. Bronstein, A. M. Bronstein, A. Wolf, and R. Kimmel, “Group-valued regularization framework for motion segmentation of dynamic non-rigid shapes,” in 3rd International Conference on Scale Space and Variational Methods in Computer Vision, Ein-Gedi, Israel, 2012, vol. 6667, pp. 725–736.
Rosman G, Bronstein MM, Bronstein AM, Wolf A, Kimmel R. 2012. Group-valued regularization framework for motion segmentation of dynamic non-rigid shapes. 3rd International Conference on Scale Space and Variational Methods in Computer Vision. SSVM: Scale Space and Variational Methods in Computer Vision, LNCS, vol. 6667, 725–736.
Rosman, Guy, et al. “Group-Valued Regularization Framework for Motion Segmentation of Dynamic Non-Rigid Shapes.” 3rd International Conference on Scale Space and Variational Methods in Computer Vision, vol. 6667, Springer Nature, 2012, pp. 725–36, doi:10.1007/978-3-642-24785-9_61.
Google Scholar
ISBN Search