论文标题
svnet：在哪里（3）均衡符合点云表示的二进制
SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representation
论文作者
论文摘要
在3D点云上的应用程序越来越需要效率和鲁棒性，在自动驾驶和机器人技术等场景中无处不在使用边缘设备，这通常需要实时和可靠的响应。该论文通过设计一个通用框架来解决挑战，以构建具有（3）等效性和网络二元化的3D学习体系结构。然而，幼稚的等模化网络和二元化会导致优化的计算效率或几何歧义。我们建议在网络中找到标量和向量特征，以避免这两种情况。确切地说，标量特征的存在使网络的主要部分是可动的，而向量特征则可以保留丰富的结构信息并确保SO（3）均衡。提出的方法可以应用于PointNet和DGCNN等一般骨干。同时，对ModelNet40，Shapenet和Real-World数据集ScanObjectnn进行的实验表明，该方法在效率，旋转稳定性和准确性之间取决于巨大的权衡。这些代码可在https://github.com/zhuoinoulu/svnet上找到。
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.
