conference paper published yes Jonathan Pokrass author Alexander Bronstein author 58f3726e-7cba-11ef-ad8b-e6e8cb3904e60000-0001-9699-8730 Michael M. Bronstein author SSVM: Scale Space and Variational Methods in Computer Vision Finding a match between partially available deformable shapes is a challenging problem with numerous applications. The problem is usually approached by computing local descriptors on a pair of shapes and then establishing a point-wise correspondence between the two. In this paper, we introduce an alternative correspondence-less approach to matching fragments to an entire shape undergoing a non-rigid deformation. We use diffusion geometric descriptors and optimize over the integration domains on which the integral descriptors of the two parts match. The problem is regularized using the Mumford-Shah functional. We show an efficient discretization based on the Ambrosio-Tortorelli approximation generalized to triangular meshes. Experiments demonstrating the success of the proposed method are presented. Springer Nature2012Ein-Gedi, Israel eng 0302-9743 1611-3349 978364224784210.1007/978-3-642-24785-9_50 6667592 - 603 yes Pokrass J, Bronstein AM, Bronstein MM. 2012. A correspondence-less approach to matching of deformable 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, 592–603. Pokrass, Jonathan, et al. “A Correspondence-Less Approach to Matching of Deformable Shapes.” <i>3rd International Conference on Scale Space and Variational Methods in Computer Vision</i>, vol. 6667, Springer Nature, 2012, pp. 592–603, doi:<a href="https://doi.org/10.1007/978-3-642-24785-9_50">10.1007/978-3-642-24785-9_50</a>. Pokrass, Jonathan, Alex M. Bronstein, and Michael M. Bronstein. “A Correspondence-Less Approach to Matching of Deformable Shapes.” In <i>3rd International Conference on Scale Space and Variational Methods in Computer Vision</i>, 6667:592–603. Springer Nature, 2012. <a href="https://doi.org/10.1007/978-3-642-24785-9_50">https://doi.org/10.1007/978-3-642-24785-9_50</a>. J. Pokrass, A.M. Bronstein, M.M. Bronstein, in:, 3rd International Conference on Scale Space and Variational Methods in Computer Vision, Springer Nature, 2012, pp. 592–603. Pokrass J, Bronstein AM, Bronstein MM. A correspondence-less approach to matching of deformable shapes. In: <i>3rd International Conference on Scale Space and Variational Methods in Computer Vision</i>. Vol 6667. Springer Nature; 2012:592-603. doi:<a href="https://doi.org/10.1007/978-3-642-24785-9_50">10.1007/978-3-642-24785-9_50</a> J. Pokrass, A. M. Bronstein, and M. M. Bronstein, “A correspondence-less approach to matching of deformable shapes,” in <i>3rd International Conference on Scale Space and Variational Methods in Computer Vision</i>, Ein-Gedi, Israel, 2012, vol. 6667, pp. 592–603. Pokrass, J., Bronstein, A. M., &#38; Bronstein, M. M. (2012). A correspondence-less approach to matching of deformable shapes. In <i>3rd International Conference on Scale Space and Variational Methods in Computer Vision</i> (Vol. 6667, pp. 592–603). Ein-Gedi, Israel: Springer Nature. <a href="https://doi.org/10.1007/978-3-642-24785-9_50">https://doi.org/10.1007/978-3-642-24785-9_50</a> 183422024-10-15T11:20:54Z2025-01-16T12:59:38Z