论文标题
点向量：点云分析中的向量表示
PointVector: A Vector Representation In Point Cloud Analysis
论文作者
论文摘要
在点云分析中，近年来基于点的方法迅速发展。这些方法最近集中在简明的MLP结构上，例如PointNext，这些结构与卷积和变压器结构相竞争。但是，标准MLP的有效提取本地特征的能力受到限制。为了解决此限制，我们提出了一个面向矢量的点集抽象，该抽象可以通过高维矢量汇总相邻的特征。为了促进网络优化，我们使用基于3D矢量旋转的独立角度构建了从标量到向量的转换。最后，我们开发了一个遵循点式结构的点向量模型。我们的实验结果表明，在S3DIS区域5和$ \ textbf {78.4 \％miou} $上，点向量实现了最先进的性能$ \ textbf {72.3 \％miou} $，s3dis上的$ \ textbf {78.4 \％miou} $（仅为6倍跨validation），只有$ \ textbf $ \ textbf = $ \ textbf ^ $} $}。我们希望我们的工作将有助于探索简洁有效的功能表示。该代码将很快发布。
In point cloud analysis, point-based methods have rapidly developed in recent years. These methods have recently focused on concise MLP structures, such as PointNeXt, which have demonstrated competitiveness with Convolutional and Transformer structures. However, standard MLPs are limited in their ability to extract local features effectively. To address this limitation, we propose a Vector-oriented Point Set Abstraction that can aggregate neighboring features through higher-dimensional vectors. To facilitate network optimization, we construct a transformation from scalar to vector using independent angles based on 3D vector rotations. Finally, we develop a PointVector model that follows the structure of PointNeXt. Our experimental results demonstrate that PointVector achieves state-of-the-art performance $\textbf{72.3\% mIOU}$ on the S3DIS Area 5 and $\textbf{78.4\% mIOU}$ on the S3DIS (6-fold cross-validation) with only $\textbf{58\%}$ model parameters of PointNeXt. We hope our work will help the exploration of concise and effective feature representations. The code will be released soon.
