Pith. sign in

REVIEW 11 cited by

Point Cloud Mamba: Point Cloud Learning via State Space Model

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.00762 v4 pith:V53GB5D6 submitted 2024-03-01 cs.CV

Tao Zhang , Haobo Yuan , Lu Qi , Jiangning Zhang , Qianyu Zhou , Shunping Ji , Shuicheng Yan , Xiangtai Li This is my paper
classification cs.CV
keywords pointcloudmambaeffectivelydatamiousequencessota
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recently, state space models have exhibited strong global modeling capabilities and linear computational complexity in contrast to transformers. This research focuses on applying such architecture to more efficiently and effectively model point cloud data globally with linear computational complexity. In particular, for the first time, we demonstrate that Mamba-based point cloud methods can outperform previous methods based on transformer or multi-layer perceptrons (MLPs). To enable Mamba to process 3-D point cloud data more effectively, we propose a novel Consistent Traverse Serialization method to convert point clouds into 1-D point sequences while ensuring that neighboring points in the sequence are also spatially adjacent. Consistent Traverse Serialization yields six variants by permuting the order of \textit{x}, \textit{y}, and \textit{z} coordinates, and the synergistic use of these variants aids Mamba in comprehensively observing point cloud data. Furthermore, to assist Mamba in handling point sequences with different orders more effectively, we introduce point prompts to inform Mamba of the sequence's arrangement rules. Finally, we propose positional encoding based on spatial coordinate mapping to inject positional information into point cloud sequences more effectively. Point Cloud Mamba surpasses the state-of-the-art (SOTA) point-based method PointNeXt and achieves new SOTA performance on the ScanObjectNN, ModelNet40, ShapeNetPart, and S3DIS datasets. It is worth mentioning that when using a more powerful local feature extraction module, our PCM achieves 79.6 mIoU on S3DIS, significantly surpassing the previous SOTA models, DeLA and PTv3, by 5.5 mIoU and 4.9 mIoU, respectively.

Discussion (0). Sign in to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. StruMamba3D: Exploring Structural Mamba for Self-supervised Point Cloud Representation Learning

    cs.CV 2025-06 conditional novelty 7.0 of 10

    A self-supervised point cloud model that encodes spatial structure into SSM latent states and adapts state-update scale to input length achieves new SOTA on ScanObjectNN and ModelNet40.

  2. FPSGen: Flexible Point Cloud Scene Generation with BEV-Supported Transport Flows

    cs.CV 2026-07 conditional novelty 6.5 of 10

    A two-stage flow-matching model that seeds point-cloud generation from a generated BEV density map, using teacher-estimated point pairings to keep transport paths straight, achieves SOTA JSD/IoU on SemanticKITTI compl...

  3. MeshMamba: State Space Models for Articulated 3D Mesh Generation and Reconstruction

    cs.CV 2025-07 conditional novelty 6.0 of 10

    MeshMamba applies Mamba state space models to dense 3D articulated mesh generation and single-image human mesh recovery, reaching over 10,000 vertices with competitive accuracy and faster inference than transformers.

  4. MambaFusion: Height-Fidelity Dense Global Fusion for Multi-modal 3D Object Detection

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A camera-LiDAR 3D detector built around a hybrid local-global Mamba block with height-fidelity LiDAR encoding reports 75.0 NDS on nuScenes validation, outperforming prior transformer-based fusion methods.

  5. FlowRAM: Grounding Flow Matching Policy with Region-Aware Mamba Framework for Robotic Manipulation

    cs.RO 2025-06 conditional novelty 6.0 of 10

    FlowRAM pairs a shrinking 3D attention region with flow-matching action generation and a Mamba fusion model, setting new RLBench state-of-the-art results.

  6. UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A point cloud pre-training method that uses 3D Gaussian splatting rendering and cross-modal image features to work for both objects and scenes.

  7. HydraMamba: Multi-Head State Space Model for Global Point Cloud Learning

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A state space model based point cloud network with shuffled Hilbert serialization, a convolutional bidirectional S6 branch, and multi-head S6 achieves new top scores on ModelNet40, ShapeNet, S3DIS, and ScanObjectNN.

  8. PointLAMA: Latent Attention meets Mamba for Efficient Point Cloud Pretraining

    cs.CV 2025-07 conditional novelty 5.0 of 10

    PointLAMA inserts a point-wise latent attention block into a Mamba point cloud encoder and adds feature-space diffusion pretraining, reporting modest benchmark gains over PointMamba.

  9. Ambiguity-aware Point Cloud Segmentation by Adaptive Margin Contrastive Learning

    cs.CV 2025-07 conditional novelty 5.0 of 10

    A point-wise ambiguity measure from label disagreement is used to tune contrastive margins per point, improving 3D indoor segmentation on S3DIS and ScanNet.

  10. MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition

    cs.CV 2025-06 conditional novelty 5.0 of 10

    MoMa adapts frozen CLIP to video by injecting Mamba-computed scale and bias into each layer, improving accuracy and efficiency on multiple action recognition benchmarks.

  11. HybridTM: Combining Transformer and Mamba for 3D Semantic Segmentation

    cs.CV 2025-07 conditional novelty 4.0 of 10

    A new 3D semantic segmentation architecture that interleaves attention and Mamba operators within each layer achieves small but consistent gains on indoor and outdoor benchmarks.

Pith tools