Department of Computer Science, Technical University of Kaiserslautern, 67663 Kaiserslautern, Germany.
Mindgarage, Technical University of Kaiserslautern, 67663 Kaiserslautern, Germany.
Sensors (Basel). 2021 Nov 6;21(21):7392. doi: 10.3390/s21217392.
In this paper, we present the idea of Self Supervised learning on the shape completion and classification of point clouds. Most 3D shape completion pipelines utilize AutoEncoders to extract features from point clouds used in downstream tasks such as classification, segmentation, detection, and other related applications. Our idea is to add contrastive learning into AutoEncoders to encourage global feature learning of the point cloud classes. It is performed by optimizing triplet loss. Furthermore, local feature representations learning of point cloud is performed by adding the Chamfer distance function. To evaluate the performance of our approach, we utilize the PointNet classifier. We also extend the number of classes for evaluation from 4 to 10 to show the generalization ability of the learned features. Based on our results, embeddings generated from the contrastive AutoEncoder enhances shape completion and classification performance from 84.2% to 84.9% of point clouds achieving the state-of-the-art results with 10 classes.
在本文中，我们提出了基于自监督学习的点云形状完成和分类的想法。大多数 3D 形状完成流水线利用自动编码器从点云中提取特征，用于下游任务，如分类、分割、检测和其他相关应用。我们的想法是在自动编码器中添加对比学习，以鼓励点云类别的全局特征学习。它是通过优化三元组损失来实现的。此外，通过添加 Chamfer 距离函数来对点云的局部特征表示进行学习。为了评估我们方法的性能，我们使用了 PointNet 分类器。我们还将类别的数量从 4 扩展到 10 进行评估，以展示学习特征的泛化能力。根据我们的结果，来自对比自动编码器的嵌入可以将点云的形状完成和分类性能从 84.2%提高到 84.9%，在 10 个类别中达到了最先进的结果。
