Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes. (arXiv:2208.06671v3 [cs.CV] UPDATED)

Few-shot segmentation of point cloud remains a challenging task, as there is
no effective way to convert local point cloud information to global
representation, which hinders the generalization ability of point features. In
this study, we propose a bidirectional feature globalization (BFG) approach,
which leverages the similarity measurement between point features and prototype
vectors to embed global perception to local point features in a bidirectional
fashion. With point-to-prototype globalization (Po2PrG), BFG aggregates local
point features to prototypes according to similarity …

arxiv cloud feature globalization segmentation semantic