Point2Node: Correlation Learning of Dynamic-Node for Point Cloud Feature Modeling
This work addresses feature modeling in point clouds for applications like 3D vision, presenting a novel method rather than an incremental improvement.
The paper tackles the problem of modeling correlations among points in point clouds by proposing Point2Node, a novel end-to-end graph model that dynamically integrates spatial correlations and adaptively aggregates features, achieving state-of-the-art performance on various benchmarks.
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.