Rotation Invariant Point Cloud Classification: Where Local Geometry Meets Global Topology
It addresses a critical challenge in 3D computer vision for applications like robotics and autonomous driving, though it is an incremental improvement over prior methods.
The paper tackled the problem of achieving rotation invariance in point cloud classification for real-world unaligned data by proposing LGR-Net, which combines local geometry and global topology, and demonstrated state-of-the-art performance on rotation-augmented datasets like ModelNet40 and ScanObjectNN.
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.