arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2010.03318cs.CV
收藏

三维点云的旋转不变局部到全局表示学习

Rotation-Invariant Local-to-Global Representation Learning for 3D Point Cloud

Seoul National University(首尔大学)

Seohyun Kim, Jaeyoo Park, Bohyung Han

摘要:

我们提出了一个局部到全局的表示学习算法的三维点云数据,这是适当的处理各种几何变换,特别是旋转,没有明确的数据增强的转换。我们的模型利用基于图卷积神经网络的多级抽象,它构造了一个描述符层次结构,以自底向上的方式编码输入对象的旋转不变形状信息。每一层的描述符是通过对3D点的随机采样从基于图的神经网络中获得的,这有效地使学习的表示对输入数据的变化具有鲁棒性。该算法在旋转增强的3D物体识别和分割基准测试中表现出了最先进的性能,并通过全面的烧蚀实验进一步分析了其特性。

英文摘要:

We propose a local-to-global representation learning algorithm for 3D point cloud data, which is appropriate to handle various geometric transformations, especially rotation, without explicit data augmentation with respect to the transformations. Our model takes advantage of multi-level abstraction based on graph convolutional neural networks, which constructs a descriptor hierarchy to encode rotation-invariant shape information of an input object in a bottom-up manner. The descriptors in each level are obtained from a neural network based on a graph via stochastic sampling of 3D points, which is effective in making the learned representations robust to the variations of input data. The proposed algorithm presents the state-of-the-art performance on the rotation-augmented 3D object recognition and segmentation benchmarks, and we further analyze its characteristics through comprehensive ablative experiments.

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。

↑