论文标题
位置对结构注意变形金刚的点云识别
Point Cloud Recognition with Position-to-Structure Attention Transformers
论文作者
论文摘要
在本文中，我们提出了位置对结构的注意变压器（PS-Former），这是一种基于变压器的算法，用于3D点云识别。 PS形式处理3D点云表示中的挑战，其中点没有位于固定网格结构中，并且功能描述有限（仅3D坐标（$ x，y，z $）用于分散点）。该域中的现有基于变压器的架构通常需要一个预先指定的功能工程步骤来提取点功能。在这里，我们在PS形式中介绍了两个新方面：1）可学习的冷凝层，可执行点降采样和特征提取； 2）递归递归富集结构信息的位置注意机制，其位置注意力分支。与竞争方法相比，虽然具有较小的启发式功能设计，但PS-Former在三个3D点云任务（包括分类，零件细分和场景分割）上展示了竞争性实验结果。
In this paper, we present Position-to-Structure Attention Transformers (PS-Former), a Transformer-based algorithm for 3D point cloud recognition. PS-Former deals with the challenge in 3D point cloud representation where points are not positioned in a fixed grid structure and have limited feature description (only 3D coordinates ($x, y, z$) for scattered points). Existing Transformer-based architectures in this domain often require a pre-specified feature engineering step to extract point features. Here, we introduce two new aspects in PS-Former: 1) a learnable condensation layer that performs point downsampling and feature extraction; and 2) a Position-to-Structure Attention mechanism that recursively enriches the structural information with the position attention branch. Compared with the competing methods, while being generic with less heuristics feature designs, PS-Former demonstrates competitive experimental results on three 3D point cloud tasks including classification, part segmentation, and scene segmentation.
