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

Learning discriminative feature directly on point clouds is still challengingin the understanding of 3D shapes. Recent methods usually partition pointclouds into local region sets, and then extract the local region features withfixed-size CNN or MLP, and finally aggregate all individual local features intoa global feature using simple max pooling. However, due to the irregularity andsparsity in sampled point clouds, it is hard to encode the fine-grainedgeometry of local regions and their spatial relationships when only using thefixed-size filters and individual local feature integration, which limit theability to learn discriminative features. To address this issue, we present anovel Local-Region-Context Network (LRC-Net), to learn discriminative featureson point clouds by encoding the fine-grained contexts inside and among localregions simultaneously. LRC-Net consists of two main modules. The first module,named intra-region context encoding, is designed for capturing the geometriccorrelation inside each local region by novel variable-size convolution filter.The second module, named inter-region context encoding, is proposed forintegrating the spatial relationships among local regions based on spatialsimilarity measures. Experimental results show that LRC-Net is competitive withstate-of-the-art methods in shape classification and shape segmentationapplications.

LRC-Net: Learning Discriminative Features on Point Clouds by Encoding Local Region Contexts