Semantic segmentation is crucial for interpreting point cloud data and plays a fundamental role in automating the creation of as-built BIM. Existing neural network models for semantic segmentation often heavily rely on the training dataset, resulting in a significant performance drop when applied to new datasets. This paper presents AttTransNet, a neural network model for automated point cloud semantic segmentation. Its attention-based pooling module improves local feature extraction from point clouds while reducing computational costs. The transfer learning framework enhances segmentation accuracy with minimal training on target datasets. Comparative experiments show that AttTransNet reduces training time by 80 % and improves segmentation accuracy by over 20 % compared with other SOTA methods. Cross-dataset experiments reveal that the transfer learning framework increases accuracy on new datasets by 150 %. By adding semantic information to point clouds, AttTransNet aids BIM modelers with direct reference, encouraging broader application of automated point cloud segmentation in the industry.

中文翻译：

---

用于具有可转移性的室内点云语义分割的深度学习网络


语义分割对于解释点云数据至关重要，并且在自动创建竣工 BIM 方面发挥着重要作用。用于语义分割的现有神经网络模型通常严重依赖训练数据集，导致应用于新数据集时性能显著下降。本文介绍了 AttTransNet，这是一种用于自动点云语义分割的神经网络模型。其基于注意力的池化模块改进了从点云中提取局部特征的能力，同时降低了计算成本。迁移学习框架通过对目标数据集进行最少的训练来提高分割准确性。比较实验表明，与其他 SOTA 方法相比，AttTransNet 将训练时间缩短了 80%，分割精度提高了 20% 以上。跨数据集实验表明，迁移学习框架将新数据集的准确性提高了 150%。通过向点云添加语义信息，AttTransNet 为 BIM 建模者提供了直接参考，鼓励自动点云分割在行业中更广泛地应用。