Point cloud completion aims to generate a complete and high-fidelity point cloud from an initially incomplete and low-quality input. A prevalent strategy involves leveraging Transformer-based models to encode global features and facilitate the reconstruction process. However, the adoption of pooling operations to obtain global feature representations often results in the loss of local details within the point cloud. Moreover, the attention mechanism inherent in Transformers introduces additional computational complexity, rendering it challenging to handle long sequences effectively. To address these issues, we propose 3DMambaComplete, a point cloud completion network built on the novel Mamba framework. It comprises three modules: HyperPoint Generation encodes point cloud features using Mamba's selection mechanism and predicts a set of Hyperpoints. A specific offset is estimated, and the down-sampled points become HyperPoints. The HyperPoint Spread module disperses these HyperPoints across different spatial locations to avoid concentration. Finally, a deformation method transforms the 2D mesh representation of HyperPoints into a fine-grained 3D structure for point cloud reconstruction. Extensive experiments conducted on various established benchmarks demonstrate that 3DMambaComplete surpasses state-of-the-art point cloud completion methods, as confirmed by qualitative and quantitative analyses.

中文翻译：

---

3DMambaComplete：探索点云补全的结构化状态空间模型

点云补全旨在从最初不完整且低质量的输入生成完整且高保真的点云。一种流行的策略是利用基于 Transformer 的模型来编码全局特征并促进重建过程。然而，采用池化操作来获取全局特征表示通常会导致点云内局部细节的丢失。此外，变形金刚固有的注意力机制引入了额外的计算复杂性，使得有效处理长序列具有挑战性。为了解决这些问题，我们提出了 3DMambaComplete，这是一个基于新颖的 Mamba 框架构建的点云补全网络。它包含三个模块： HyperPoint Generation 使用 Mamba 的选择机制对点云特征进行编码并预测一组 Hyperpoint。估计特定的偏移量，并且下采样的点成为 HyperPoints。 HyperPoint Spread 模块将这些 HyperPoint 分散在不同的空间位置，以避免集中。最后，变形方法将 HyperPoints 的 2D 网格表示转换为用于点云重建的细粒度 3D 结构。在各种既定基准上进行的大量实验表明，3DMambaComplete 超越了最先进的点云完成方法，这一点已通过定性和定量分析得到证实。