Remarkable advancements have been made recently in point cloud analysis through the exploration of transformer architecture, but it remains challenging to effectively learn local and global structures within point clouds. In this paper, we propose a new transformer network equipped with a collect-and-distribute mechanism to communicate short- and long-range contexts of point clouds, which we refer to as CDFormer. Specifically, we first employ self-attention to capture short-range interactions within each local patch, and the updated local features are then collected into a set of proxy reference points from which we can extract long-range contexts. Afterward, we distribute the learned long-range contexts back to local points via cross-attention. To address the position clues for short- and long-range contexts, we additionally introduce the context-aware position encoding to facilitate position-aware communications between points. We perform experiments on five popular point cloud datasets, namely ModelNet40, ScanObjectNN, ShapeNetPart, S3DIS and ScanNetV2, for classification and segmentation. Results show the effectiveness of the proposed CDFormer, delivering several new state-of-the-art performances on point cloud classification and segmentation tasks. The source code is available at \url{https://github.com/haibo-qiu/CDFormer}.

翻译：近年来，通过探索Transformer架构，点云分析领域取得了显著进展，但有效学习点云中的局部与全局结构仍具挑战性。本文提出一种配备收集-分发机制的新型Transformer网络（称为CDFormer），用于实现点云短程与长程上下文的通信。具体而言，我们首先利用自注意力捕获每个局部块内的短程相互作用，然后将更新后的局部特征收集至一组代理参考点，从中提取长程上下文。随后，通过交叉注意力将学习到的长程上下文分发回局部点。为处理短程与长程上下文的位置线索，我们额外引入上下文感知位置编码，以促进点之间的位置感知通信。我们在五个主流点云数据集（ModelNet40、ScanObjectNN、ShapeNetPart、S3DIS与ScanNetV2）上进行了分类与分割实验。结果表明，所提出的CDFormer具有有效性，在点云分类与分割任务上实现了多项新的最佳性能。源代码已公开于\url{https://github.com/haibo-qiu/CDFormer}。