Point2Node: Correlation Learning of Dynamic-Node for Point Cloud Feature Modeling


  • Wenkai Han Xiamen University
  • Chenglu Wen Xiamen University
  • Cheng Wang Xiamen University
  • Xin Li Louisiana State University
  • Qing Li Xiamen University




Fully exploring correlation among points in point clouds is essential for their feature modeling. This paper presents a novel end-to-end graph model, named Point2Node, to represent a given point cloud. Point2Node can dynamically explore correlation among all graph nodes from different levels, and adaptively aggregate the learned features. Specifically, first, to fully explore the spatial correlation among points for enhanced feature description, in a high-dimensional node graph, we dynamically integrate the node's correlation with self, local, and non-local nodes. Second, to more effectively integrate learned features, we design a data-aware gate mechanism to self-adaptively aggregate features at the channel level. Extensive experiments on various point cloud benchmarks demonstrate that our method outperforms the state-of-the-art.




How to Cite

Han, W., Wen, C., Wang, C., Li, X., & Li, Q. (2020). Point2Node: Correlation Learning of Dynamic-Node for Point Cloud Feature Modeling. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 10925-10932. https://doi.org/10.1609/aaai.v34i07.6725



AAAI Technical Track: Vision