Skeleton based shape matching and retrieval

By Hari Sundar, Deborah Silver, N. Gagvani, Sven J. Dickinson. 2003 Shape Modeling International., 2003

686 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/c1ee55c51d2b6511c9f9595703eb6806b6a2756e

How researchers see this paper

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

In Aerospace Engineering

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Improved Adversarial Systems for 3D Object Generation and Reconstruction (2017, background): “Several of these shape models have been shown in practical applications such as interactive editing [20] and reconstructing room geometry from a single image [4, 24, 13].”
Curve-Skeleton Properties, Applications, and Algorithms (2007, methodology): “Another application is matching of 3D objects: Given a query object, the task is to find similar or identical objects in a database by using the curve-skeleton [27], [33], [53], [118].”
3D Skeletons: A State‐of‐the‐Art Report (2016, methodology): “Curve skeletons compactly represent a shape as the graph of its components, their relationship and, in some cases, a rough description of their geometry [BFS00,SSGD03].”
Shape google: Geometric words and expressions for invariant shape retrieval (2011, methodology): “Graph-based methods based on skeletons [Sundar et al. 2003] and Reeb graphs [Hilaga et al. 2001; Biasotti et al. 2003; Tung and Schmitt 2005] are capable of dealing with deformations, for example, matching articulated shapes.”
Model Composition from Interchangeable Components (2007, methodology): “Skeleton based methods [ 24 , 5] are more robust to changes in pose but typically do not distinguish between symmetric skeleton branches such as arms or legs.”
Contextual Part Analogies in 3D Objects (2010, background): “Many works focus on the need to define measures for similarity of shapes ( Sundar et al. 2003; Cornea et al. 2005; Funkhouser et al. 2005), alignment of shapes (Gelfand et al. 2005) and finding complete correspondence between two models for the purposes of deformations, morphing (Alexa 2002), and c”
Joint embeddings of shapes and images via CNN image purification (2015, methodology): “Another type of method uses graph representations in order to obtain a topological description of the shape [Hilaga et al. 2001; Chen and Ouhyoung 2002; Sundar et al. 2003].”
The Cross-Depiction Problem: Computer Vision Algorithms for Recognising Objects in Artwork and in Photographs (2015, methodology): “[55] use skeletal graph to represent shape and use graph matching techniques to match and compare skeletons.”
Three-dimensional shape searching: state-of-the-art review and future trends (2005, neutral): “[119] presented a skeletal graph-based method using distance transform.”
Point Cloud Skeletons via Laplacian Based Contraction (2010, neutral): “Applications which utilize curve skeletons for shape analysis and processing include segmentation ([1], [2], [3], [4]), object matching and retrieval ([5], [6], [7]), surface reconstruction ([8], [9]), and animation ([4], [10], [11], [12], [13], [14]), among others.”
Retrieving Articulated 3-D Models Using Medial Surfaces and Their Graph Spectra (2005, background): “They have also been demonstrated in the context of matching 3-D object models with tubular parts, using a centerline approximation of the 3-D skeleton [29].”
A survey of content based 3D shape retrieval methods (2004, methodology): “ogy and radial distance about the edge [76].”