Electors Voting for Fast Automatic Shape Correspondence

dc.contributor.authorKin-Chung Au, Oscaren_US
dc.contributor.authorTai, Chiew-Lanen_US
dc.contributor.authorCohen-Or, Danielen_US
dc.contributor.authorZheng, Youyien_US
dc.contributor.authorFu, Hongboen_US
dc.date.accessioned2015-02-23T16:41:59Z
dc.date.available2015-02-23T16:41:59Z
dc.date.issued2010en_US
dc.description.abstractThis paper challenges the difficult problem of automatic semantic correspondence between two given shapes which are semantically similar but possibly geometrically very different (e.g., a dog and an elephant). We argue that the challenging part is the establishment of a sparse correspondence and show that it can be efficiently solved by considering the underlying skeletons augmented with intrinsic surface information. To avoid potentially costly direct search for the best combinatorial match between two sets of skeletal feature nodes, we introduce a statistical correspondence algorithm based on a novel voting scheme, which we call electors voting. The electors are a rather large set of correspondences which then vote to synthesize the final correspondence. The electors are selected via a combinatorial search with pruning tests designed to quickly filter out a vast majority of bad correspondence. This voting scheme is both efficient and insensitive to parameter and threshold settings. The effectiveness of the method is validated by precision-recall statistics with respect to manually defined ground truth. We show that high quality correspondences can be instantaneously established for a wide variety of model pairs, which may have different poses, surface details, and only partial semantic correspondence.en_US
dc.description.number2en_US
dc.description.seriesinformationComputer Graphics Forumen_US
dc.description.volume29en_US
dc.identifier.doi10.1111/j.1467-8659.2009.01634.xen_US
dc.identifier.issn1467-8659en_US
dc.identifier.pages645-654en_US
dc.identifier.urihttps://doi.org/10.1111/j.1467-8659.2009.01634.xen_US
dc.publisherThe Eurographics Association and Blackwell Publishing Ltden_US
dc.titleElectors Voting for Fast Automatic Shape Correspondenceen_US
Files