We propose a general method for deep learning based point cloud analysis, which is invariant to rotation on the inputs. Classical methods are vulnerable to rotation, as they usually take aligned point clouds as input. Principle Component Analysis (PCA) is a practical approach to achieve rotation invariance. However, there are still some gaps between theory and practical algorithms. In this work, we present a thorough study on designing rotation invariant algorithms for point cloud analysis. We first formulate it as a permutation invariant problem, then propose a general framework which can be combined with any backbones. Our method is beneficial for further research such as 3D pre-training and multi-modal learning. Experiments show that our method has considerable or better performance compared to state-of-the-art approaches on common benchmarks. Code is available at https://github.com/luoshuqing2001/RI_framework.

翻译：我们提出了一种基于深度学习的点云分析通用方法，该方法对输入旋转具有不变性。传统方法通常将对齐后的点云作为输入，因此易受旋转影响。主成分分析（PCA）是实现旋转不变性的实用途径，但理论与实际算法之间仍存在差距。本文对设计旋转不变点云分析算法进行了深入研究：首先将其形式化为置换不变问题，进而提出一个可与任意骨干网络结合的通用框架。该方法对三维预训练与多模态学习等后续研究具有促进作用。实验表明，在常用基准测试中，本方法性能与最先进技术相当或更优。代码已开源：https://github.com/luoshuqing2001/RI_framework。