# ZigzagPointMamba: Spatial-Semantic Mamba for Point Cloud Understanding

arXiv: https://arxiv.org/abs/2505.21381 · HTML: https://mlsanity.com/paper/2505.21381/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Point clouds, detection and remote sensing, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 6 of its 10 references that are in the map.
- First posted on arXiv 27 May 2025.

## Placed in

- State-space sequence models (S4, Mamba) / [Point clouds, detection and remote sensing](https://mlsanity.com/ssm/point-clouds-detection-and-remote-sensing/)

## Builds on (most cited first, 6 of 6)

- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [PCT: Point cloud transformer](https://mlsanity.com/paper/2012.09688/) (2020)
- [U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation](https://mlsanity.com/paper/2401.04722/) (2024)
- [Masked Discrimination for Self-Supervised Learning on Point Clouds](https://mlsanity.com/paper/2203.11183/) (2022)
- [Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentation](https://mlsanity.com/paper/2402.05079/) (2024)
- [PointMT: Efficient Point Cloud Analysis with Hybrid MLP-Transformer Architecture](https://mlsanity.com/paper/2408.05508/) (2024)

## Built on by (most cited first, 7 of 7)

- [Mantis: Mamba-native Tuning is Efficient for 3D Point Cloud Foundation Models](https://mlsanity.com/paper/2605.03438/) (2026)
- [Rethinking Convergence in Deep Learning: The Predictive-Corrective Paradigm for Anatomy-Informed Brain MRI Segmentation](https://mlsanity.com/paper/2510.15439/) (2025)
- [Taming the Light: Illumination-Invariant Semantic 3DGS-SLAM](https://mlsanity.com/paper/2511.22968/) (2025)
- [Robust 3DGS-based SLAM via Adaptive Kernel Smoothing](https://mlsanity.com/paper/2511.23221/) (2025)
- [DM3D: Dynamic Mamba via Offset-Guided Feature Resampling for Point Cloud Understanding](https://mlsanity.com/paper/2512.03424/) (2025)
- [MIND: Decoupling Model-Induced Label Noise via Latent Manifold Disentanglement](https://mlsanity.com/paper/2605.16081/) (2026)
- [PointCHR: Point Cloud Analysis via Curvature-Aware Hyperbolic Rectification](https://mlsanity.com/paper/2607.24052/) (2026)

## Abstract (arXiv)

State Space models (SSMs) such as PointMamba enable efficient feature extraction for point cloud self-supervised learning with linear complexity, outperforming Transformers in computational efficiency. However, existing PointMamba-based methods depend on complex token ordering and random masking, which disrupt spatial continuity and local semantic correlations. We propose ZigzagPointMamba to tackle these challenges. The core of our approach is a simple zigzag scan path that globally sequences point cloud tokens, enhancing spatial continuity by preserving the proximity of spatially adjacent point tokens. Nevertheless, random masking undermines local semantic modeling in self-supervised learning. To address this, we introduce a Semantic-Siamese Masking Strategy (SMS), which masks semantically similar tokens to facilitate reconstruction by integrating local features of original and similar tokens. This overcomes the dependence on isolated local features and enables robust global semantic modeling. Our pre-trained ZigzagPointMamba weights significantly improve downstream tasks, achieving a 1.59% mIoU gain on ShapeNetPart for part segmentation, a 0.4% higher accuracy on ModelNet40 for classification, and 0.19%, 1.22%, and 0.72% higher accuracies respectively for the classification tasks on the OBJ-BG, OBJ-ONLY, and PB-T50-RS subsets of ScanObjectNN.