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.
翻译:3D点云的应用日益需要效率和稳健性,在自动驾驶和机器人等情景下普遍使用边缘装置,往往需要实时和可靠的反应。文件通过设计一个总框架来应对挑战,以SO(3) 等同和网络二进制构建3D学习架构。然而,变异网络和二进制的天真的结合,要么造成亚最佳计算效率或几何模糊性。我们提议在我们的网络中找到标度和矢量功能,以避免两种情况发生。确切地说,卡路里特性的存在使网络的主要部分可以分解,而矢量特性有助于保留丰富的结构信息,确保SO(3) 等等等等QD学习结构。提议的方法可以适用于PointNet和DGCNN。同时,模型Net40、ShapeNet和真实世界数据集ScanObjectNN的实验表明,该方法在效率、轮换稳健性和准确性之间实现了巨大的平衡。在https://github.com/zhouulous/vnets上提供了代码。