Deep learning approach has been used extensively in image analysis tasks. However, implementing the methods in 3D data is a bit complex because most of the previously designed deep learning architectures used 1D or 2D as input. In this work, the performance of deep learning methods on different 3D data representations has been reviewed. Based on the categorization of the different 3D data representations proposed in this paper, the importance of choosing a suitable 3D data representation which depends on simplicity, usability, and efficiency has been highlighted. Furthermore, the origin and contents of the major 3D datasets were discussed in detail. Due to growing interest in 3D object retrieval and classification tasks, the performance of different 3D object retrieval and classification on ModelNet40 dataset were compared. According to the findings in this work, multi views methods surpass voxel-based methods and with increased layers and enough data augmentation the performance can still be increased. Therefore, it can be concluded that deep learning together with a suitable 3D data representation gives an effective approach for improving the performance of 3D shape analysis. Finally, some possible directions for future researches were suggested.

中文翻译：

---

检索和分类中 3D 数据表示的深度学习方法综述


深度学习方法已广泛应用于图像分析任务。然而，在 3D 数据中实现这些方法有点复杂，因为大多数先前设计的深度学习架构都使用 1D 或 2D 作为输入。在这项工作中，回顾了深度学习方法在不同 3D 数据表示上的性能。基于本文提出的不同 3D 数据表示的分类，强调了选择合适的 3D 数据表示的重要性，这取决于简单性、可用性和效率。此外，还详细讨论了主要 3D 数据集的起源和内容。由于人们对 3D 对象检索和分类任务的兴趣日益浓厚，我们对 ModelNet40 数据集上不同 3D 对象检索和分类的性能进行了比较。根据这项工作的发现，多视图方法超越了基于体素的方法，并且通过增加层数和足够的数据增强，性能仍然可以提高。因此，可以得出结论，深度学习与合适的 3D 数据表示相结合，为提高 3D 形状分析的性能提供了一种有效的方法。最后，提出了未来研究的一些可能的方向。