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/

Zendy Plus

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

Zendy Tools

Zendy Open

We propose a precise and efficient normal estimation method that can dealwith noise and nonuniform density for unstructured 3D point clouds. Unlikeexisting approaches that directly take patches and ignore the localneighborhood relationships, which make them susceptible to challenging regionssuch as sharp edges, we propose to learn graph convolutional featurerepresentation for normal estimation, which emphasizes more local neighborhoodgeometry and effectively encodes intrinsic relationships. Additionally, wedesign a novel adaptive module based on the attention mechanism to integratepoint features with their neighboring features, hence further enhancing therobustness of the proposed normal estimator against point density variations.To make it more distinguishable, we introduce a multi-scale architecture in thegraph block to learn richer geometric features. Our method outperformscompetitors with the state-of-the-art accuracy on various benchmark datasets,and is quite robust against noise, outliers, as well as the density variations.

GraphFit: Learning Multi-scale Graph-Convolutional Representation for Point Cloud Normal Estimation