Abstract | ||
---|---|---|
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. (c) 2021 Elsevier B.V. All rights reserved. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1016/j.patrec.2021.08.010 | PATTERN RECOGNITION LETTERS |
Keywords | DocType | Volume |
Point cloud classification, Rotation invariance, 3D Deep learning | Journal | 151 |
ISSN | Citations | PageRank |
0167-8655 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ruibin Gu | 1 | 0 | 0.34 |
Qiuxia Wu | 2 | 9 | 3.20 |
Wing W. Y. Ng | 3 | 528 | 56.12 |
Hongbin Xu | 4 | 0 | 1.69 |
Zhiyong Wang | 5 | 550 | 51.76 |