Show simple item record

dc.contributor.authorZheng, Youyien_US
dc.contributor.authorCohen-Or, Danielen_US
dc.contributor.authorAverkiou, Melinosen_US
dc.contributor.authorMitra, Niloy J.en_US
dc.contributor.editorB. Levy and J. Kautzen_US
dc.date.accessioned2015-03-03T12:26:39Z
dc.date.available2015-03-03T12:26:39Z
dc.date.issued2014en_US
dc.identifier.issn1467-8659en_US
dc.identifier.urihttp://dx.doi.org/10.1111/cgf.12309en_US
dc.description.abstractExtracting semantically related parts across models remains challenging, especially without supervision. The common approach is to co-analyze a model collection, while assuming the existence of descriptive geometric features that can directly identify related parts. In the presence of large shape variations, common geometric features, however, are no longer sufficiently descriptive. In this paper, we explore an indirect top-down approach, where instead of part geometry, part arrangements extracted from each model are compared. The key observation is that while a direct comparison of part geometry can be ambiguous, part arrangements, being higher level structures, remain consistent, and hence can be used to discover latent commonalities among semantically related shapes. We show that our indirect analysis leads to the detection of recurring arrangements of parts, which are otherwise difficult to discover in a direct unsupervised setting. We evaluate our algorithm on ground truth datasets and report advantages over geometric similarity-based bottom-up co-segmentation algorithms.en_US
dc.publisherThe Eurographics Association and John Wiley and Sons Ltd.en_US
dc.titleRecurring Part Arrangements in Shape Collectionsen_US
dc.description.seriesinformationComputer Graphics Forumen_US


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record