Point cloud analysis is a fundamental task in 3D computer vision. Most previous works have conducted experiments on synthetic datasets with well-aligned data; while real-world point clouds are often not pre-aligned. How to achieve rotation invariance remains an open problem in point cloud analysis. To meet this challenge, we propose a novel approach toward achieving rotation-invariant (RI) representations by combining local geometry with global topology. In our local-global-representation (LGR)-Net, we have designed a two-branch network where one stream encodes local geometric RI features and the other encodes global topology-preserving RI features. Motivated by the observation that local geometry and global topology have different yet complementary RI responses in varying regions, two-branch RI features are fused by an innovative multi-layer perceptron (MLP) based attention module. To the best of our knowledge, this work is the first principled approach toward adaptively combining global and local information under the context of RI point cloud analysis. Extensive experiments have demonstrated that our LGR-Net achieves the state-of-the-art performance on various rotation-augmented versions of ModelNet40, ShapeNet, ScanObjectNN, and S3DIS.
翻译:3D 计算机愿景的基本任务是云层分析3D 。 以往的多数工作都对包含相近数据的合成数据集进行了实验; 真实点云往往没有预先确定。 如何实现轮换变化仍然是点云分析的一个未解决的问题。 为了应对这一挑战,我们提出了一个创新的方法,通过将本地几何与全球地貌学相结合来实现轮换变化(RI)的表达。 在我们的本地全球代表(LGR)网络中,我们设计了一个两分网络,其中一条串编码了本地几何RI特征和其他编码了全球地表学保存RI的特征。 广泛的实验显示,我们的LGR-Net在不同地区有不同但互为补充的RI反应,因此,两个分支的RI功能由基于关注的创新性多层次感官模块(MLP)结合。 根据我们的知识,这是在RI 点云分析背景下对适应性地合并全球和本地信息的第一个原则方法。 广泛的实验表明,我们的LGR-40Net 模型和全球地名录3在各种轨道上实现了州- 网络的旋转, 和Scal-DIS-DIS-DIS-DIS-DIS- scar- dival- depal- disal- disal- depmental- disal- disal- disal- disal- disal- disal- dal- disal- dal- dal- dal- dal- dal- dal- dept- dal- dalmentmentmentmentmentmentmental- deptal- dept- disald- dept- sal- stramentmentmentald.