Discovering inter-point connection for efficient high-dimensional feature extraction from point coordinate is a key challenge in processing point cloud. Most existing methods focus on designing efficient local feature extractors while ignoring global connection, or vice versa. In this paper, we design a new Inductive Bias-aided Transformer (IBT) method to learn 3D inter-point relations, which considers both local and global attentions. Specifically, considering local spatial coherence, local feature learning is performed through Relative Position Encoding and Attentive Feature Pooling. We incorporate the learned locality into the Transformer module. The local feature affects value component in Transformer to modulate the relationship between channels of each point, which can enhance self-attention mechanism with locality based channel interaction. We demonstrate its superiority experimentally on classification and segmentation tasks. The code is available at: https://github.com/jiamang/IBT

翻译：从点坐标中挖掘点间关联以实现高效的高维特征提取是点云处理中的关键挑战。现有方法大多侧重于设计高效的局部特征提取器而忽略全局关联，或反之。本文设计了一种新型归纳偏置辅助Transformer（IBT）方法，用于学习三维点间关系，同时兼顾局部与全局注意力。具体而言，通过相对位置编码与注意力特征池化实现局部特征学习，并将学习到的局部性融入Transformer模块。局部特征影响Transformer中的值分量，以调节每个点通道间的关系，从而增强基于局部通道交互的自注意力机制。我们在分类和分割任务上实验证明了其优越性。代码地址：https://github.com/jiamang/IBT