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

In this paper, we propose one novel model for point cloud semanticsegmentation, which exploits both the local and global structures within thepoint cloud based on the contextual point representations. Specifically, weenrich each point representation by performing one novel gated fusion on thepoint itself and its contextual points. Afterwards, based on the enrichedrepresentation, we propose one novel graph pointnet module, relying on thegraph attention block to dynamically compose and update each pointrepresentation within the local point cloud structure. Finally, we resort tothe spatial-wise and channel-wise attention strategies to exploit the pointcloud global structure and thereby yield the resulting semantic label for eachpoint. Extensive results on the public point cloud databases, namely the S3DISand ScanNet datasets, demonstrate the effectiveness of our proposed model,outperforming the state-of-the-art approaches. Our code for this paper isavailable at https://github.com/fly519/ELGS.

Exploiting Local and Global Structure for Point Cloud Semantic Segmentation with Contextual Point Representations