Canonical Forms for Non-Rigid 3D Shape Retrieval

dc.contributor.authorPickup, Daviden_US
dc.contributor.authorSun, Xianfangen_US
dc.contributor.authorRosin, Paul L.en_US
dc.contributor.authorMartin, Ralph R.en_US
dc.contributor.authorCheng, Zhiquanen_US
dc.contributor.authorNie, Sipinen_US
dc.contributor.authorJin, Longcunen_US
dc.contributor.editorI. Pratikakis and M. Spagnuolo and T. Theoharis and L. Van Gool and R. Veltkampen_US
dc.date.accessioned2015-04-27T11:03:39Z
dc.date.available2015-04-27T11:03:39Z
dc.date.issued2015en_US
dc.description.abstractWe present a new benchmark for testing algorithms that create canonical forms for use in non-rigid 3D shape retrieval. We have combined two existing datasets to create a varied collection of models for testing. Canonical forms attempt to factor out a shape's pose, giving a pose-neutral shape. This opens up the possibility of using methods originally designed for rigid retrieval for the task of non-rigid shape retrieval. We demonstrate the benchmark by using it to compare the performance of nine canonical form methods, using three different retrieval algorithms.en_US
dc.description.sectionheadersSHREC'15 Tracksen_US
dc.description.seriesinformationEurographics Workshop on 3D Object Retrievalen_US
dc.identifier.doi10.2312/3dor.20151063en_US
dc.identifier.pages99-106en_US
dc.identifier.urihttps://doi.org/10.2312/3dor.20151063en_US
dc.publisherThe Eurographics Associationen_US
dc.titleCanonical Forms for Non-Rigid 3D Shape Retrievalen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
099-106.pdf
Size:
7.39 MB
Format:
Adobe Portable Document Format
Collections