On Bending Invariant Signatures for Surfaces

By A. Elad, Ron Kimmel. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003

510 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/a2b743429c55258ac8b8b32c7ffc559a9f744752

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Robust 3D Shape Correspondence in the Spectral Domain (2006, methodology): “Elad and Kimmel [10] make use of geodesic”
Shape Classification Using the Inner-Distance (2007, methodology): “In this section, the inner-distance is used to build articulation invariant signatures for 2D shapes using multidimensional scaling (MDS) similar to [12].”
Three-Dimensional Face Recognition (2005, unknown): “Following Elad and Kimmel (2001, 2003), the image of {x 1 , . . . , x N } under ϕ is called the canonical form of (S, g).”
Gromov–Wasserstein Distances and the Metric Approach to Object Matching (2011, methodology): “An example in a similar spirit is given by the problem of comparing faces under different expressions or objects in different poses [37].”
Image Matching from Handcrafted to Deep Features: A Survey (2020, background): “A traditional approach is proposed by Elad and Kimmel (2003) to match shapes by embedding them in an intermediate Euclidean space.”
Mesh segmentation using feature point and core extraction (2005, background): “Bending has only a minor influence on the geodesic distances [7].”
Laplace-Beltrami eigenfunctions for deformation invariant shape representation (2007, unknown): “Such representations were used for shape classiﬁcation [EK03,JZ07], part correspondence [JZ06], and segmentation [KLT05].”
Möbius voting for surface correspondence (2009, background): “A less expensive approach is to embed the mesh in a (possibly higher dimension) space such that the Euclidean distance between two embedded points is an approximation of the geodesic distance on the original mesh [Elad and Kimmel 2003; Jain et al. 2007; Ovsjanikov et al. 2008].”