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

Few-shot segmentation of point cloud remains a challenging task, as there isno effective way to convert local point cloud information to globalrepresentation, which hinders the generalization ability of point features. Inthis study, we propose a bidirectional feature globalization (BFG) approach,which leverages the similarity measurement between point features and prototypevectors to embed global perception to local point features in a bidirectionalfashion. With point-to-prototype globalization (Po2PrG), BFG aggregates localpoint features to prototypes according to similarity weights from dense pointfeatures to sparse prototypes. With prototype-to-point globalization (Pr2PoG),the global perception is embedded to local point features based on similarityweights from sparse prototypes to dense point features. The sparse prototypesof each class embedded with global perception are summarized to a singleprototype for few-shot 3D segmentation based on the metric learning framework.Extensive experiments on S3DIS and ScanNet demonstrate that BFG significantlyoutperforms the state-of-the-art methods.

Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes