Handle URI:
http://hdl.handle.net/10754/598683
Title:
Joint shape segmentation with linear programming
Authors:
Huang, Qixing; Koltun, Vladlen; Guibas, Leonidas
Abstract:
We present an approach to segmenting shapes in a heterogenous shape database. Our approach segments the shapes jointly, utilizing features from multiple shapes to improve the segmentation of each. The approach is entirely unsupervised and is based on an integer quadratic programming formulation of the joint segmentation problem. The program optimizes over possible segmentations of individual shapes as well as over possible correspondences between segments from multiple shapes. The integer quadratic program is solved via a linear programming relaxation, using a block coordinate descent procedure that makes the optimization feasible for large databases. We evaluate the presented approach on the Princeton segmentation benchmark and show that joint shape segmentation significantly outperforms single-shape segmentation techniques. © 2011 ACM.
Citation:
Huang Q, Koltun V, Guibas L (2011) Joint shape segmentation with linear programming. Proceedings of the 2011 SIGGRAPH Asia Conference on - SA ’11. Available: http://dx.doi.org/10.1145/2024156.2024159.
Publisher:
Association for Computing Machinery (ACM)
Journal:
Proceedings of the 2011 SIGGRAPH Asia Conference on - SA '11
Issue Date:
2011
DOI:
10.1145/2024156.2024159
Type:
Conference Paper
Sponsors:
We are grateful to Mirela Ben-Chen, Siddhartha Chaudhuri, and Evangelos Kalogerakis for their comments on this paper. This work was supported in part by NSF grants 0808515 and 1011228, a Stanford-KAUST AEA grant, and a Stanford Graduate Fellowship.
Appears in Collections:
Publications Acknowledging KAUST Support

Full metadata record

DC FieldValue Language
dc.contributor.authorHuang, Qixingen
dc.contributor.authorKoltun, Vladlenen
dc.contributor.authorGuibas, Leonidasen
dc.date.accessioned2016-02-25T13:34:23Zen
dc.date.available2016-02-25T13:34:23Zen
dc.date.issued2011en
dc.identifier.citationHuang Q, Koltun V, Guibas L (2011) Joint shape segmentation with linear programming. Proceedings of the 2011 SIGGRAPH Asia Conference on - SA ’11. Available: http://dx.doi.org/10.1145/2024156.2024159.en
dc.identifier.doi10.1145/2024156.2024159en
dc.identifier.urihttp://hdl.handle.net/10754/598683en
dc.description.abstractWe present an approach to segmenting shapes in a heterogenous shape database. Our approach segments the shapes jointly, utilizing features from multiple shapes to improve the segmentation of each. The approach is entirely unsupervised and is based on an integer quadratic programming formulation of the joint segmentation problem. The program optimizes over possible segmentations of individual shapes as well as over possible correspondences between segments from multiple shapes. The integer quadratic program is solved via a linear programming relaxation, using a block coordinate descent procedure that makes the optimization feasible for large databases. We evaluate the presented approach on the Princeton segmentation benchmark and show that joint shape segmentation significantly outperforms single-shape segmentation techniques. © 2011 ACM.en
dc.description.sponsorshipWe are grateful to Mirela Ben-Chen, Siddhartha Chaudhuri, and Evangelos Kalogerakis for their comments on this paper. This work was supported in part by NSF grants 0808515 and 1011228, a Stanford-KAUST AEA grant, and a Stanford Graduate Fellowship.en
dc.publisherAssociation for Computing Machinery (ACM)en
dc.subjectLinear programmingen
dc.subjectShape correspondenceen
dc.subjectShape segmentationen
dc.titleJoint shape segmentation with linear programmingen
dc.typeConference Paperen
dc.identifier.journalProceedings of the 2011 SIGGRAPH Asia Conference on - SA '11en
dc.contributor.institutionStanford University, Palo Alto, United Statesen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.