Learning Part Boundaries from 3D Point Clouds

Simple item page
dc.contributor.authorLoizou, Mariosen_US
dc.contributor.authorAverkiou, Melinosen_US
dc.contributor.authorKalogerakis, Evangelosen_US
dc.contributor.editorJacobson, Alec and Huang, Qixingen_US
dc.date.accessioned2020-07-05T13:26:15Z
dc.date.available2020-07-05T13:26:15Z
dc.date.issued2020
dc.description.abstractWe present a method that detects boundaries of parts in 3D shapes represented as point clouds. Our method is based on a graph convolutional network architecture that outputs a probability for a point to lie in an area that separates two or more parts in a 3D shape. Our boundary detector is quite generic: it can be trained to localize boundaries of semantic parts or geometric primitives commonly used in 3D modeling. Our experiments demonstrate that our method can extract more accurate boundaries that are closer to ground-truth ones compared to alternatives. We also demonstrate an application of our network to fine-grained semantic shape segmentation, where we also show improvements in terms of part labeling performance.en_US
dc.description.number5
dc.description.sectionheadersSurface Reconstruction
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume39
dc.identifier.doi10.1111/cgf.14078
dc.identifier.issn1467-8659
dc.identifier.pages183-195
dc.identifier.urihttps://doi.org/10.1111/cgf.14078
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14078
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectComputing methodologies
dc.subjectNeural networks
dc.subjectPoint
dc.subjectbased models
dc.subjectShape analysis
dc.titleLearning Part Boundaries from 3D Point Cloudsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
v39i5pp183-195.pdf
Size:
1.52 MB
Format:
Adobe Portable Document Format
Download
Collections
39-Issue 5