Unsupervised co-segmentation of a set of shapes via descriptor-space spectral clustering

By Oana Sidi, Oliver Matias van Kaick, Yanir Kleiman, Hao Zhang, Daniel Cohen-Or. 2011

258 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Unsupervised co-segmentation for 3D shapes using iterative multi-label optimization (2013, methodology): “Rather than focusing on local features, we aim at extracting the global similarities of the patches.”
Learning part-based templates from large collections of 3D shapes (2013, methodology): “…surfaces while ignoring the part structure of objects [Kim et al. 2012a]; consistent segmentation algorithms decompose polygonal models into consistent sets of parts but do not compute point-to-point correspondences [Golovinskiy and Funkhouser 2009] or model shape variation [Sidi et al. 2011].”
Deformation-driven shape correspondence via shape recognition (2017, background): “Co-analysis [Golovinskiy and Funkhouser 2009; Hu et al. 2016; Huang et al. 2014; Kim et al. 2013; Sidi et al. 2011; van Kaick et al. 2013; Xu et al. 2010, 2012; Zheng et al. 2014] also utilizes weak knowledge from shape collections, but doing so in a di erent manner from our work.”
3D Shape Segmentation and Labeling via Extreme Learning Machine (2014, unknown): “On the unsupervised side, clustering methods has been utilized for segmentation and labeling [SvKK ∗ 11, HFL12].”
Learning 3D Part Detection from Sparsely Labeled Data (2014, background): “The problem of mesh labeling has largely been approached via segmentation (see [20], [8], [10], [22]).”
Interactive shape co-segmentation via label propagation (2014, methodology): “& 2013 Published by Elsevier Ltd.”
3D Shape Segmentation with Projective Convolutional Networks (2016, methodology): “); then, a clustering method or classifier infers part labels for elements based on their descriptors; and finally (optionally) a separate graph cuts step is employed to smooth out the surface labeling [26, 41, 43, 19, 58].”
Active co-analysis of a set of shapes (2012, methodology): “Recently, there is an increasing interest in the co-analysis of sets of shapes, since current works have shown that more information can be extracted by simultaneously analyzing a set, rather than analyzing each shape individually [Golovinskiy and Funkhouser 2009; Xu et al. 2010; Sidi et al. 2011].”
Projective analysis for 3D shape segmentation (2013, background): “Scaling along horizontal direction is achieved through pixel-to-pixel correspondence search during the label transfer step; see Section 5.2.”
Learning Shape Abstractions by Assembling Volumetric Primitives (2016, background): “By virtue of these properties, our representation can enable several applications related to shape similarity, part discovery, perception and shape manipulation.”