点Transformer用于三维和ALS屋顶PointClouds的形状分类和检索
Point Transformer for Shape Classification and Retrieval of 3D and ALS Roof PointClouds
摘要：
深度学习方法的成功使三维点云处理任务在遥感应用中取得了重大突破。现有的方法利用具有一些限制的卷积，因为它们假设均匀的输入分布并且不能学习长期依赖性。最近的研究表明，在这些方法的同时增加注意力可以提高性能。这就提出了一个问题：注意力层能完全取代卷积吗？本文提出了一个完全注意力模型-- { \em Point Transformer}，用于导出丰富的点云表示。该模型的形状分类和检索性能进行了评估的大规模城市数据集-RoofN 3D和标准基准数据集ModelNet 40。大量的实验进行了测试模型的鲁棒性看不见的点腐败分析其在真实数据集上的有效性。所提出的方法在RoofN 3D数据集中优于其他最先进的模型，在ModelNet 40基准测试中给出了有竞争力的结果，并对各种看不见的点损坏表现出高鲁棒性。此外，与其他方法相比，该模型具有高度的内存和空间效率。
英文摘要：
The success of deep learning methods led to significant breakthroughs in 3-D point cloud processing tasks with applications in remote sensing. Existing methods utilize convolutions that have some limitations, as they assume a uniform input distribution and cannot learn long-range dependencies. Recent works have shown that adding attention in conjunction with these methods improves performance. This raises a question: can attention layers completely replace convolutions? This paper proposes a fully attentional model - {\em Point Transformer}, for deriving a rich point cloud representation. The model's shape classification and retrieval performance are evaluated on a large-scale urban dataset - RoofN3D and a standard benchmark dataset ModelNet40. Extensive experiments are conducted to test the model's robustness to unseen point corruptions for analyzing its effectiveness on real datasets. The proposed method outperforms other state-of-the-art models in the RoofN3D dataset, gives competitive results in the ModelNet40 benchmark, and showcases high robustness to various unseen point corruptions. Furthermore, the model is highly memory and space efficient when compared to other methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
