The Canonically Posed 3D Objects Dataset

dc.contributor.authorPapadakis, Panagiotisen_US
dc.contributor.editorBenjamin Bustos and Hedi Tabia and Jean-Philippe Vandeborre and Remco Veltkampen_US
dc.date.accessioned2014-12-15T13:52:05Z
dc.date.available2014-12-15T13:52:05Z
dc.date.issued2014en_US
dc.description.abstractShape matching methodologies of generic 3D objects are conventionally preceded by a pose normalization stage, that transforms objects to a canonical coordinate frame wherein feature extraction and shape matching is performed. Arguably, the canonical pose of a 3D object depends not only on its geometry but also on its semantic meaning, a characteristic that generally complicates the extraction of ground truth data. This paper introduces the first ground-truth dataset of 3D objects that allows an objective evaluation of methods which obtain the canonical pose of objects within extrinsic space. By virtue of the protocol that was followed to assemble the dataset, 3D objects of the same class share a fixed pose in terms of object center, scale and rotation while undergoing diverse shape deformations. The dataset is publicly disclosed and relevant use cases are discussed.en_US
dc.description.seriesinformationEurographics Workshop on 3D Object Retrievalen_US
dc.identifier.isbn978-3-905674-58-3en_US
dc.identifier.issn1997-0463en_US
dc.identifier.urihttps://doi.org/10.2312/3dor.20141047en_US
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/3dor.20141047.033-036
dc.publisherThe Eurographics Associationen_US
dc.titleThe Canonically Posed 3D Objects Dataseten_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
033-036.pdf
Size:
506.18 KB
Format:
Adobe Portable Document Format
Collections