This paper explores various learning strategies for 3D building type
classification and part segmentation on the BuildingNet dataset. ULIP with
PointNeXt and PointNeXt segmentation are extended for the classification and
segmentation task on BuildingNet dataset. The best multi-task PointNeXt-s model
with multi-modal pretraining achieves 59.36 overall accuracy for 3D building
type classification, and 31.68 PartIoU for 3D building part segmentation on
validation split. The final PointNeXt XL model achieves 31.33 PartIoU and 22.78
ShapeIoU on test split for BuildingNet-Points segmentation, which significantly
improved over PointNet++ model reported from BuildingNet paper, and it won the
1st place in the BuildingNet challenge at CVPR23 StruCo3D workshop.

本文旨在探究基于 BuildingNet 数据集的 3D 建筑类型分类和部件分割的多种学习策略，提出了使用扩展的 ULIP、PointNeXt 和 PointNeXt 分割方法进行分类和分割任务的解决方案。在多模态预训练的前提下，最佳的多任务 PointNeXt-s 模型在验证集上达到了 59.36% 的准确率和 31.68 的 PartIoU，PointNeXt XL 模型在 BuildingNet-Points 分割测试集上达到了 31.33 的 PartIoU 和 22.78 的 ShapeIoU，显著提高了建筑网络论文中所述的 PointNet ++ 模型的性能，并在 CVPR23 StruCo3D 工作室的 BuildingNet 挑战中获得了第一名。