English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We introduce, TextureNet, a neural network architecture designed to extractfeatures 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-RoSyfields have several properties favorable for convolution on surfaces (lowdistortion, few singularities, consistent parameterization, etc.), orientationsare ambiguous up to 4-fold rotation at any sample point. So, we introduce a newconvolutional operator invariant to the 4-RoSy ambiguity and use it in anetwork to extract features from high-resolution signals on geodesicneighborhoods of a surface. In comparison to alternatives, such as PointNetbased methods which lack a notion of orientation, the coherent structure givenby these neighborhoods results in significantly stronger features. As anexample application, we demonstrate the benefits of our architecture for 3Dsemantic segmentation of textured 3D meshes. The results show that our methodoutperforms all existing methods on the basis of mean IoU by a significantmargin in both geometry-only (6.4%) and RGB+Geometry (6.9-8.2%) settings.

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