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.
SVNet : where SO(3) equivariance meets binarization on point cloud representation
|Author:||Su, Zhuo1; Welling, Max2; Pietikainen, Matti1;|
1Center for Machine Vision and Signal Analysis, University of Oulu, Finland
2AMLab, University of Amsterdam, Netherlands
3National University of Defense Technology, China
|Online Access:||PDF Full Text (PDF, 1.7 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe2023040334847
Institute of Electrical and Electronics Engineers,
|Publish Date:|| 2023-04-03
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.
International Conference on 3D Vision proceedings
|Pages:||547 - 556|
2022 International Conference on 3D Vision (3DV)
International Conference on 3D Vision
|Type of Publication:||
A4 Article in conference proceedings
|Field of Science:||
113 Computer and information sciences
This work was partially supported by National Key Research and Development Program of China No. 2021YFB3100800, the Academy of Finland under grant 331883 and the National Natural Science Foundation of China under Grant 61872379 and 62022091. The CSC IT Center for Science, Finland, is also acknowledged for computational resources.
|Academy of Finland Grant Number:||
331883 (Academy of Finland Funding decision)
© 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.