A general framework for rotation invariant point cloud analysis
CoRR(2024)
摘要
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.
更多查看译文
关键词
Point cloud learning,rotation invariant,PCA,general framework
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要