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.

翻译：在点云分析中，基于点的方法近年来迅速发展。这些方法近期聚焦于简洁的MLP结构（如PointNeXt），展现出与卷积和Transformer结构相竞争的能力。然而，标准MLP在有效提取局部特征方面存在局限性。为解决该局限，我们提出一种面向向量的点集抽象方法，可通过更高维向量聚合邻域特征。为促进网络优化，我们基于三维向量旋转，利用独立角度构建从标量到向量的变换。最终，我们开发出遵循PointNeXt结构的PointVector模型。实验结果表明，PointVector在S3DIS Area 5上实现了$\textbf{72.3\% mIOU}$的最优性能，在S3DIS（6折交叉验证）上达到$\textbf{78.4\% mIOU}$，而模型参数仅为PointNeXt的$\textbf{58\%}$。我们期望本研究有助于探索简洁高效的特征表示。代码将稍后开源。