Transformer with its underlying attention mechanism and the ability to capture long-range dependencies makes it become a natural choice for unordered point cloud data. However, separated local regions from the general sampling architecture corrupt the structural information of the instances, and the inherent relationships between adjacent local regions lack exploration, while local structural information is crucial in a transformer-based 3D point cloud model. Therefore, in this paper, we propose a novel module named Local Context Propagation (LCP) to exploit the message passing between neighboring local regions and make their representations more informative and discriminative. More specifically, we use the overlap points of adjacent local regions (which statistically show to be prevalent) as intermediaries, then re-weight the features of these shared points from different local regions before passing them to the next layers. Inserting the LCP module between two transformer layers results in a significant improvement in network expressiveness. Finally, we design a flexible LCPFormer architecture equipped with the LCP module. The proposed method is applicable to different tasks and outperforms various transformer-based methods in benchmarks including 3D shape classification and dense prediction tasks such as 3D object detection and semantic segmentation. Code will be released for reproduction.

翻译：Transformer凭借其内在的注意力机制与捕获长距离依赖的能力，已成为处理无序点云数据的自然选择。然而，通用采样架构中离散的局部区域会破坏实例的结构信息，且相邻局部区域间的内在关联缺乏探索——而局部结构信息对于基于Transformer的三维点云模型至关重要。为此，本文提出名为局部上下文传播（LCP）的新型模块，通过挖掘相邻局部区域间的消息传递机制，使区域表征更具信息量与判别力。具体而言，我们利用统计上普遍存在的相邻局部区域重叠点作为中介，在将特征传递至后续网络层前，对不同局部区域中这些共享点的特征进行权重重新分配。将LCP模块插入两个Transformer层之间后，网络表达能力获得显著提升。最终，我们设计了配备LCP模块的灵活LCPFormer架构。该方法适用于多种任务，在三维形状分类及密集预测任务（如三维目标检测与语义分割）等基准测试中均优于各类Transformer方法。代码将开源以供复现研究。