Skip to main content

TextureNet: Consistent Local Parametrizations for Learning From High-Resolution Signals on Meshes

Author(s): Huang, Jingwei; Zhang, Haotian; Yi, Li; Funkhouser, Thomas; Niebner, Matthias; et al

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr1fk2g
Full metadata record
DC FieldValueLanguage
dc.contributor.authorHuang, Jingwei-
dc.contributor.authorZhang, Haotian-
dc.contributor.authorYi, Li-
dc.contributor.authorFunkhouser, Thomas-
dc.contributor.authorNiebner, Matthias-
dc.contributor.authorGuibas, Leonidas J-
dc.date.accessioned2021-10-08T19:50:29Z-
dc.date.available2021-10-08T19:50:29Z-
dc.date.issued2019en_US
dc.identifier.citationHuang, Jingwei, Haotian Zhang, Li Yi, Thomas Funkhouser, Matthias Nießner, and Leonidas J. Guibas. "TextureNet: Consistent Local Parametrizations for Learning From High-Resolution Signals on Meshes." In IEEE/CVF Conference on Computer Vision and Pattern Recognition (2019): pp. 4435-4444. doi:10.1109/CVPR.2019.00457en_US
dc.identifier.issn1063-6919-
dc.identifier.urihttps://openaccess.thecvf.com/content_CVPR_2019/papers/Huang_TextureNet_Consistent_Local_Parametrizations_for_Learning_From_High-Resolution_Signals_on_CVPR_2019_paper.pdf-
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/pr1fk2g-
dc.description.abstractWe introduce, TextureNet, a neural network architecture designed to extract features from high-resolution signals associated with 3D surface meshes (e.g., color texture maps). The key idea is to utilize a 4-rotational symmetric(4-RoSy) field to define a domain for convolution on a surface. Though 4-RoSy fields have several properties favor-able for convolution on surfaces (low distortion, few singularities, consistent parameterization, etc.), orientations are ambiguous up to 4-fold rotation at any sample point. So, we introduce a new convolutional operator invariant to the4-RoSy ambiguity and use it in a network to extract features from high-resolution signals on geodesic neighborhoods of a surface. In comparison to alternatives, such as PointNet-based methods which lack a notion of orientation, the coherent structure given by these neighborhoods results in significantly stronger features. As an example application, we demonstrate the benefits of our architecture for 3D semantic segmentation of textured 3D meshes. The results show that our method outperforms all existing methods on the basis of mean IoU by a significant margin in both geometry-only(6.4%) and RGB+Geometry (6.9-8.2%) settings.en_US
dc.format.extent4435 - 4444en_US
dc.language.isoen_USen_US
dc.relation.ispartofIEEE/CVF Conference on Computer Vision and Pattern Recognitionen_US
dc.rightsAuthor's manuscripten_US
dc.titleTextureNet: Consistent Local Parametrizations for Learning From High-Resolution Signals on Meshesen_US
dc.typeConference Articleen_US
dc.identifier.doi10.1109/CVPR.2019.00457-
dc.identifier.eissn2575-7075-
pu.type.symplectichttp://www.symplectic.co.uk/publications/atom-terms/1.0/conference-proceedingen_US

Files in This Item:
File Description SizeFormat 
TextureNet.pdf2.44 MBAdobe PDFView/Download


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