SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representation
This addresses the need for real-time and reliable 3D perception in applications such as autonomous driving and robotics, though it is incremental as it builds on existing backbones like PointNet and DGCNN.
The paper tackled the challenge of designing efficient and robust 3D point cloud learning architectures by combining SO(3) equivariance and network binarization, achieving a trade-off between efficiency, rotation robustness, and accuracy on datasets like ModelNet40 and ScanObjectNN.
Efficiency and robustness are increasingly needed for applications on 3D point clouds, with the ubiquitous use of edge devices in scenarios like autonomous driving and robotics, which often demand real-time and reliable responses. The paper tackles the challenge by designing a general framework to construct 3D learning architectures with SO(3) equivariance and network binarization. However, a naive combination of equivariant networks and binarization either causes sub-optimal computational efficiency or geometric ambiguity. We propose to locate both scalar and vector features in our networks to avoid both cases. Precisely, the presence of scalar features makes the major part of the network binarizable, while vector features serve to retain rich structural information and ensure SO(3) equivariance. The proposed approach can be applied to general backbones like PointNet and DGCNN. Meanwhile, experiments on ModelNet40, ShapeNet, and the real-world dataset ScanObjectNN, demonstrated that the method achieves a great trade-off between efficiency, rotation robustness, and accuracy. The codes are available at https://github.com/zhuoinoulu/svnet.