Transformer-based models have significantly advanced natural language
processing and computer vision in recent years. However, due to the irregular
and disordered structure of point cloud data, transformer-based models for 3D
deep learning are still in their infancy compared to other methods. In this
paper we present Point Cross-Attention Transformer (PointCAT), a novel
end-to-end network architecture using cross-attentions mechanism for point
cloud representing. Our approach combines multi-scale features via two seprate
cross-attention transformer branches. To reduce the computational increase
brought by multi-branch structure, we further introduce an efficient model for
shape classification, which only process single class token of one branch as a
query to calculate attention map with the other. Extensive experiments
demonstrate that our method outperforms or achieves comparable performance to
several approaches in shape classification, part segmentation and semantic
segmentation tasks.

本文提出了一种基于 Point Cross-Attention Transformer 的新型端到端网络结构，将多尺度特征通过两个不同的跨注意力变换器分支进行组合，并引入一种有效的形状分类模型，通过计算不同分支的单类标记与注意图来减少计算负担，实验表明该方法在形状分类，部分分割和语义分割任务中表现优异。