Skip to main content

Structure-Aware Shape Synthesis

Author(s): Balashova, Elena; Singh, Vivek; Wang, Jiangping; Teixeira, Brian; Chen, Terrence; et al

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr1f24m
Full metadata record
DC FieldValueLanguage
dc.contributor.authorBalashova, Elena-
dc.contributor.authorSingh, Vivek-
dc.contributor.authorWang, Jiangping-
dc.contributor.authorTeixeira, Brian-
dc.contributor.authorChen, Terrence-
dc.contributor.authorFunkhouser, Thomas-
dc.date.accessioned2021-10-08T19:46:34Z-
dc.date.available2021-10-08T19:46:34Z-
dc.date.issued2018en_US
dc.identifier.citationBalashova, Elena, Vivek Singh, Jiangping Wang, Brian Teixeira, Terrence Chen, and Thomas Funkhouser. "Structure-Aware Shape Synthesis." In International Conference on 3D Vision (3DV) (2018): pp. 140-149. doi:10.1109/3DV.2018.00026en_US
dc.identifier.issn2378-3826-
dc.identifier.urihttps://arxiv.org/pdf/1808.01427.pdf-
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/pr1f24m-
dc.description.abstractWe propose a new procedure to guide training of a data-driven shape generative model using a structure-aware loss function. Complex 3D shapes often can be summarized using a coarsely defined structure which is consistent and robust across variety of observations. However, existing synthesis techniques do not account for structure during training, and thus often generate implausible and structurally unrealistic shapes. During training, we enforce structural constraints in order to enforce consistency and structure across the entire manifold. We propose a novel methodology for training 3D generative models that incorporates structural information into an end-to-end training pipeline.en_US
dc.format.extent140 - 149en_US
dc.language.isoen_USen_US
dc.relation.ispartofInternational Conference on 3D Vision (3DV)en_US
dc.rightsAuthor's manuscripten_US
dc.titleStructure-Aware Shape Synthesisen_US
dc.typeConference Articleen_US
dc.identifier.doi10.1109/3DV.2018.00026-
dc.identifier.eissn2475-7888-
pu.type.symplectichttp://www.symplectic.co.uk/publications/atom-terms/1.0/conference-proceedingen_US

Files in This Item:
File Description SizeFormat 
StructureAwareShapeSynthesis.pdf8.27 MBAdobe PDFView/Download


Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.