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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper studies 3D dense shape correspondence, a key shape analysisapplication in computer vision and graphics. We introduce a novel hybridgeometric deep learning-based model that learns geometrically meaningful anddiscretization-independent features with a U-Net model as the primary nodefeature extraction module, followed by a successive spectral-based graphconvolutional network. To create a diverse set of filters, we use anisotropicwavelet basis filters, being sensitive to both different directions andband-passes. This filter set overcomes the over-smoothing behavior ofconventional graph neural networks. To further improve the model's performance,we add a function that perturbs the feature maps in the last layer ahead offully connected layers, forcing the network to learn more discriminativefeatures overall. The resulting correspondence maps show state-of-the-artperformance on the benchmark datasets based on average geodesic errors andsuperior robustness to discretization in 3D meshes. Our approach provides newinsights and practical solutions to the dense shape correspondence research.

Anisotropic Multi-Scale Graph Convolutional Network for Dense Shape Correspondence