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

Normal estimation for unstructured point clouds is an important task in 3Dcomputer vision. Current methods achieve encouraging results by mapping localpatches to normal vectors or learning local surface fitting using neuralnetworks. However, these methods are not generalized well to unseen scenariosand are sensitive to parameter settings. To resolve these issues, we propose animplicit function to learn an angle field around the normal of each point inthe spherical coordinate system, which is dubbed as Neural Angle Fields (NeAF).Instead of directly predicting the normal of an input point, we predict theangle offset between the ground truth normal and a randomly sampled querynormal. This strategy pushes the network to observe more diverse samples, whichleads to higher prediction accuracy in a more robust manner. To predict normalsfrom the learned angle fields at inference time, we randomly sample queryvectors in a unit spherical space and take the vectors with minimal anglevalues as the predicted normals. To further leverage the prior learned by NeAF,we propose to refine the predicted normal vectors by minimizing the angleoffsets. The experimental results with synthetic data and real scans showsignificant improvements over the state-of-the-art under widely usedbenchmarks.

NeAF: Learning Neural Angle Fields for Point Normal Estimation