Dual-Stream Enhanced Point Cloud Classification Network Based on Mamba and Cyclic Maximum Pooling

点云分类作为三维视觉领域的核心任务，面临特征表达能力有限与排列不变性处理不足的双重挑战。针对传统基于多层感知机(MLP)的网络难以有效捕捉全局特征及动态聚合局部信息的问题，文章提出一种基于Mamba与循环最大池化的双流增强式点云分类网络。首先，通过引入Mamba模块对原始点云进行序列化建模，利用其长程依赖捕捉能力提取具有强区分性的全局特征；其次，加入循环最大池化(RMP)模块，通过多级迭代的池化操作显式提取点云排列不变特征，并结合循环机制实现局部特征的动态强化与上下文融合。双流架构中，全局特征与局部特征经自适应加权后输入MLP分类头，完成高阶语义推理。在ModelNet40与ScanObjectNN基准数据集上的实验表明，本文方法的分类准确率分别达到93.9%与86.8%，都高于先进的分类方法。消融实验进一步验证了Mamba的全局建模能力与RMP模块对无序点云的鲁棒性增强效果。Point cloud classification, as a core task in the field of 3D vision, is faced with the dual challenges of limited feature expressiveness and insufficient handling of alignment invariance. Aiming at the problem that traditional multilayer perceptron (MLP)-based networks can hardly effectively capture global features and dynamically aggregate local information, this paper proposes a dual-stream augmented point cloud classification network based on Mamba and cyclic max-pooling. First, the original point cloud is serialized and modeled by introducing the Mamba module, and its long-range dependency capture ability is used to extract global features with strong discriminative properties; second, the Recurrent Maximum Pooling (RMP) module is added to explicitly extract the point cloud arrangement-invariant features through multi-level iterative pooling operations, and combined with the recurrent mechanism to achieve dynamic enhancement and contextual fusion of local features. In the dual-stream architecture, global features and local features are adaptively weighted and input into the MLP classification header to complete the higher-order semantic inference. Experiments on ModelNet40 and ScanObjectNN benchmark datasets show that the classification accuracy of this paper’s method reaches 93.9% and 86.8%, respectively, both of which are higher than the state-of-the-art classification methods. The ablation experiments further validate the global modeling capability of Mamba with the robustness enhancement effect of the RMP module on disordered point clouds.