Transformer Enhanced Hierarchical 3D Point Cloud Semantic Segmentation

Point cloud can represent 3D geometry conveniently, but its challenging for computers to process it. In this work, we design a transformer enhanced hierarchical neural network for accurate large scale point cloud semantic segmentation. We use semantic space’s transformer block to learn global feature correlation. In this way, we can expand the receptive field of network to the whole input point cloud. Experimental results on S3DIS 3d semantic segmentation dataset show that, compared with the traditional hierarchical 3d semantic segmentation model, our transformer-enhanced hierarchical model achieved higher performance on overall accuracy and mloU.

点云（Point cloud）可便捷地表征三维几何结构，但计算机对其进行处理仍颇具挑战。本研究设计了一款Transformer增强型分层神经网络，以实现高精度的大规模点云语义分割任务。我们通过语义空间中的Transformer模块学习全局特征关联，借此将网络的感受野拓展至整个输入点云。在S3DIS三维语义分割数据集上的实验结果表明，相较于传统分层三维语义分割模型，我们的Transformer增强型分层模型在总体准确率与平均交并比（mloU）上均取得了更优异的性能。

搜集汇总

背景与挑战

背景概述

该数据集专注于3D点云语义分割，通过引入Transformer增强的分层神经网络来提升性能。它利用语义空间的Transformer块学习全局特征相关性，扩展网络感受野至整个点云，实验在S3DIS数据集上验证了其在整体准确率和mIoU上的优越表现。