ERINet: Enhanced rotation-invariant network for point cloud classification

作者：Gu, Ruibin; Wu, Qiuxia^*; Ng, Wing W. Y.; Xu, Hongbin; Wang, Zhiyong

来源：PATTERN RECOGNITION LETTERS, 2021, 151: 180-186.

DOI：10.1016/j.patrec.2021.08.010

• Point cloud classification
• Rotation invariance
• 3D Deep learning

Point cloud classification has attracted increasing attention due to the outstanding performance of elab-orated networks on synthetic datasets. However, rotation invariance has been seldom investigated. In this paper, we propose a straightforward rotation-invariant network called ERINet with a novel enhanced rotation-invariant module for point cloud classification. The enhanced rotation-invariant module is com-posed of a representation conversion component and a feature aggregation layer. It first takes 12 well-designed rotation-invariant features as the representation of point cloud and leverages the feature aggre-gation layer to aggregate the features of neighbor points into a discriminative rotation-invariant repre-sentation. The enhanced rotation-invariant module is further combined with the multi-layer perceptron and the fully connected layers to form an efficient ERINet. The proposed ERINet demonstrated its advan-tages with a small model size and high speed. The enhanced rotation-invariant module of our ERINet is also extensible and can be easily integrated with mainstream networks to improve rotation robustness. The experimental results on rotation-augmented datasets demonstrate that our ERINet outperforms other state-of-the-art methods in rotation robustness for point cloud classification.