SVNet : where SO(3) equivariance meets binarization on point cloud representation
Su, Zhuo; Welling, Max; Pietikainen, Matti; Liu, Li (2023-02-22)
Z. Su, M. Welling, M. Pietikäinen and L. Liu, "SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representation," 2022 International Conference on 3D Vision (3DV), Prague, Czech Republic, 2022, pp. 547-556, doi: 10.1109/3DV57658.2022.00084.
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
https://rightsstatements.org/vocab/InC/1.0/
https://urn.fi/URN:NBN:fi-fe2023040334847
Tiivistelmä
Abstract
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.
Kokoelmat
- Avoin saatavuus [34516]