Segmentation of 3D meshes through spectral clustering

By Rong Liu, Hao Zhang. 2004

295 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design

How researchers see this paper

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

In Computational Mechanics

In Computer Graphics and Computer-Aided Design

Citations in the corpus

SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation (2016, methodology): “In the domain of unsupervised shape segmentation, there is one family of methods [15, 16] emphasizing the effectiveness of spectral analysis for 3D shape segmentation.”
Mesh Segmentation - A Comparative Study (2006, background): “Semantics-oriented approaches to shape segmentation have gained a great interest recently in the research community [5, 20, 28, 19, 34, 32, 15, 18, 16, 14, 25], because they can support parametrization or re-meshing schemes, metamorphosis, 3D shape retrieval, skeleton extraction as well as the model”
Mesh segmentation using feature point and core extraction (2005, methodology): “Many methods use clustering techniques, such as region growing [4, 24], iterative clustering [31], spectral clustering [23], feature point-based clustering [33, 35], and fuzzy clustering with graph cuts [15].”
Learning 3D mesh segmentation and labeling (2010, methodology): “Specifically, we use a JointBoost classifier [Shotton et al. 2009; Torralba et al. 2007], summarized in Section 3.3.”
Min-cut based segmentation of point clouds (2009, methodology): “A wide variety of algorithms have been proposed for this problem, including ones based on convex decomposition [2], watershed analysis [12], K-means [17], hierarchical clustering [4, 5], region growing [19], and spectral clustering [11].”
Consistent mesh partitioning and skeletonisation using the shape diameter function (2008, methodology): “Topology-based approaches as in [22], spectral analysis as in [ 18 ], and global attributes such as average geodesic distance (AGD) [10] and Reeb-graphs [2] can support some level of consistency over pose dierences of the same shape.”
Robust 3D Shape Correspondence in the Spectral Domain (2006, background): “Recently, they have found several applications in geometry processing as well, including mesh segmentation [22], spherical parameterization [16], and surface reconstruction [19].”
Parallel Spectral Clustering in Distributed Systems (2011, background): “Unfortunately, when the number of data instances (denoted by n) is large, spectral clustering can encounter a quadratic resource bottleneck [13], [25] in computing pairwise similarity among n data instances and in storing the large similarity matrix.”
Spectral Mesh Processing (2009, methodology): “…the surface No leakage problem VSI distance fields A part-aware metric Metric: graph distance on a combined weighted geodesic graph angular graph graph edge weight edge weight normalization normalization = combined graph Placed into an algorithm Early method of [Liu & Zhang 04] …”
A benchmark for 3D mesh segmentation (2009, methodology): “In a few cases, more than one algorithm have been compared on the same set of meshes (e.g., [Attene et al. 2006a]), but the evaluation is qualitative (images shown side-by-side).”